Re: [R] newton method
I'm not sure what you meant by a topic on newton's method (algorithm? demo?), but the demonstration in the package 'animation' might help: install.packages('animation') par(pch = 20) ani.options(nmax = 50) newton.method(function(x) 5 * x^3 - 7 * x^2 - 40 * x + 100, 7.15, c(-6.2, 7.1)) Regards, Yihui -- Yihui Xie xieyi...@gmail.com Phone: +86-(0)10-82509086 Fax: +86-(0)10-82509086 Mobile: +86-15810805877 Homepage: http://www.yihui.name School of Statistics, Room 1037, Mingde Main Building, Renmin University of China, Beijing, 100872, China On Mon, Mar 23, 2009 at 11:15 AM, Roslina Zakaria zrosl...@yahoo.com wrote: Hi R-users, Does R has a topic on newton's method? Thank you for the info. __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
Re: [R] Legend containing maths symbol and values of variables
I tried sprintf and paste, which solves one of my problem i.e. replacing the variable name by its value. However, = is not renderend correctly as the inequality symbol. On Tue, Mar 24, 2009 at 12:24 PM, Gabor Grothendieck ggrothendi...@gmail.com wrote: For the legend argument try this: leg = as.expression(c(sprintf(Up (= %d), threshold), Normal, Down, NA)) or use paste in place of sprintf. On Mon, Mar 23, 2009 at 11:53 PM, Daren Tan darenta...@gmail.com wrote: I need to have the maths symbol for = in the legend, and to substitute threshold variable with its value. Somehow, various attempts weren't successful. Please help. threshold - 0.5 plot(NA, xlab=, ylab=, main=, axes=F, xlim=c(0,1), ylim=c(0,1), xaxs=i, yaxs=i) legend(x=0, y=1, fill=c(orange, white, green, gray90), cex=0.8, pt.cex=1.8, x.intersp=0.6, bg = white, legend=c(expression(Up ( = threshold )), Normal, Down, NA), bty = n) __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code. __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
[R] Calculating percentage Missing value for variables using one object
Hi, I have a dataset in which there are in all 250 variables and for each variable the data is entered over the months. I need to calculate the percentage of missing values for each variable over each month and then plot a graph for that. I am running the following code for doing the same *ds - read.csv(file=filepath, header=TRUE) attach(ds) may - length(variable1[variable1==]) / length(dos[dos==May-06]) * 100 jun - length(variable1[variable1==]) / length(dos[dos==June-06]) * 100 . . . var1 - c(may, jun, ...) x - seq(as.Date(2006-01-01), as.Date(2007-03-31), by=months) plot(var1~x)* So likewise I am calculating the percentage of missing values for each variable for each month using different variables and storing the values in those variables and then combining those variables in one object for plotting the graph. I need to know, whether can I combine all the variables from that dataset in one object and calculate the missing values percentage over months together, instead of creating different variables for each month and then combining them. Also, after doing that, I need to plot the graph for each variable and combine it in a single pdf file. I highly appreciate all your help. Thanks, Shreyasee [[alternative HTML version deleted]] __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
[R] Barplot With Selected X-Axis Region
Dear all, I have a data that looks like this: print(dat) V1 V2 1 -43342073 14 2 -433377304 3 -432846761 11372 75188572 11 11373 752061656 11374 75262720 24 What I want to do is to have a barplot where x-axis is taken from V1 and y-axis taken from V2. But I only want to plot the those region where V1 = -500 and = 500. But some how this snippet doesn't seem to work: xlim = c(-500,500) barplot(as.matrix(dat[dat$V1 = -500 dat$V1 =500,dat$V2]),xlim=xlim,axes=TRUE, main =nm); What's wrong with my approach. So yes, I do want the V1 information, hence I am aware that I dont' want: plot(hist(dat[dat =-500 dat =500])) - Gundala Viswanath Jakarta - Indonesia __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
Re: [R] If statement generates two outputs
Berwin A Turlach wrote: G'day Carl, On Mon, 23 Mar 2009 20:11:19 -0400 Carl Witthoft c...@witthoft.com wrote: From: Wacek Kusnierczyk Waclaw.Marcin.Kusnierczyk_at_idi.ntnu.no Date: Sun, 22 Mar 2009 22:58:49 +0100 just for fun, you could do this with multiassignment, e.g., using the (highly experimental and premature!) rvalues: source('http://miscell.googlecode.com/svn/rvalues/rvalues.r') if (TRUE) c(df1, df2) := list(4:8, 9:13) dput(df1) # 4:8 dput(df2) # 9:13 --- Now THAT's what I call an overloaded operator! ^_^ But seriously: can someone explain to me what's going on in the rvalues.r code? I tried a simple experiment, replacing := with a colec in the code, and of course the line c(df1, df2) colec list(4:8, 9:13) just gives me a syntax error response. Clearly I need a pointer to some documentation about how the colon and equals sign get special treatment somewhere inside R. Not sure why := gets a special treatment, perhaps because it is not a valid name and, hence, the parser deduces that it is an operator? possibly. you'd have to look into the parser code, as it has, as duncan explained, no documentation. ?Syntax doesn't mention it either, as doesn't the r language definition, as far as i can see. IIRC, the traditional way to define your own operator is to bound the name by percentage signs, i.e. replacing := by %colec% and then issuing the command c(df1, df2) %colec% list(4:8, 9:13) will work. ... and which was precisely why i wanted the simple ':=' -- because all those traditional %*% are so ugly (syntactically). vQ __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
Re: [R] How to set up a function for Central Limit Theorem
On Mon, 23 Mar 2009, pfc_ivan wrote: I tried using the for (i..) to make 1000 differents sets of numbers, but then I dont know how to get the mean value of all of them... because I dont even think 1000 different sets of numbers were made, because when i print it it always shows me the same values, basically I dont know how to replicate the funcion many times. A useful approach for this sort of simulation problem (though not the most efficient approach for this particular example) is to write a function that does one simulation one.sim-function(mu, sigma, n){ ## generate data ## compute the z-statistic return(zn) } Then you can run simulations using replicate() lots.of.zs - replicate(1000, one.sim(mu=1,sigma=2, n=10)) -thomas stephen sefick wrote: homework? On Mon, Mar 23, 2009 at 1:30 PM, pfc_ivan pfc_i...@hotmail.com wrote: Hello guys, I am stuck here: How do I make 1000 samples of n = 10 observations from an Exponential distribution and then compute the mean for all those 1000 samples? Basically I need to prove the Central Limit theorem, which states: http://www.nabble.com/file/p22664113/d175f06cbf200bd52a2c27a2e56dc594.png Where the Sn is sum of random variables, n we have from the question, mu is mean and (sigma)^2 is variance. I am having trouble setting up the function to do this. Any help apreciated! -- View this message in context: http://www.nabble.com/How-to-set-up-a-function-for-%22Central-Limit-Theorem%22-tp22664113p22664113.html Sent from the R help mailing list archive at Nabble.com. __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code. -- Stephen Sefick Let's not spend our time and resources thinking about things that are so little or so large that all they really do for us is puff us up and make us feel like gods. We are mammals, and have not exhausted the annoying little problems of being mammals. -K. Mullis __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code. -- View this message in context: http://www.nabble.com/How-to-set-up-a-function-for-%22Central-Limit-Theorem%22-tp22664113p22666250.html Sent from the R help mailing list archive at Nabble.com. __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code. Thomas Lumley Assoc. Professor, Biostatistics tlum...@u.washington.eduUniversity of Washington, Seattle __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
Re: [R] read in large data file (tsv) with inline filter?
On Mon, 23 Mar 2009, David Reiss wrote: I have a very large tab-delimited file, too big to store in memory via readLines() or read.delim(). Turns out I only need a few hundred of those lines to be read in. If it were not so large, I could read the entire file in and grep the lines I need. For such a large file; many calls to read.delim() with incrementing skip and nrows parameters, followed by grep() calls is very slow. You certainly don't want to use repeated reads from the start of the file with skip=, but if you set up a file connection fileconnection - file(my.tsv, open=r) you can read from it incrementally with readLines() or read.delim() without going back to the start each time. The speed of approach should be within a reasonable constant factor of anything else, since reading the file once is unavoidable and should be the bottleneck. -thomas Thomas Lumley Assoc. Professor, Biostatistics tlum...@u.washington.eduUniversity of Washington, Seattle __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
Re: [R] confidence interval or error of x intercept of a linear regression
On Mon, 23 Mar 2009, Kevin J Emerson wrote: Now, it is simple enough to calculate the x-intercept itself ( - intercept / slope ), but it is a whole separate process to generate the confidence interval of it. I can't figure out how to propagate the error of the slope and intercept into the ratio of the two. The option option I have tried to figure out is to use the predict function to look for where the confidence intervals cross the axis but this hasn't been too fruitful either. A few people have written code to do nonlinear transformations automatically. There's one in my 'survey' package, and I think there's an example in Venables Ripley's S Programming, and I'm sure there are others. For example library(survey) m-lm(Dev.Rate~Temperature, data=t) svycontrast(m, quote(-`(Intercept)`/Temperature)) nlcon SE contrast 3.8061 0.1975 The `backquotes` are necessary because the coefficient name, (Intercept), isn't a legal variable name. The svycontrast() function works on anything that has coef() and vcov() methods. The actual delta-method computations are in survey:::nlcon -thomas Thomas Lumley Assoc. Professor, Biostatistics tlum...@u.washington.eduUniversity of Washington, Seattle __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
Re: [R] confidence interval or error of x intercept of a linear regression
I should probably also add the health warning that the delta-method approach to ratios of coefficients is REALLY BAD unless the denominator is well away from zero. When the denominator is near zero nothing really works (Fieller's method is valid but only because 'valid' means less than you might like for a confidence interval method, and the bootstrap is useful but not necessarily valid) -thomas Thomas Lumley Assoc. Professor, Biostatistics tlum...@u.washington.eduUniversity of Washington, Seattle __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
Re: [R] If statement generates two outputs
Berwin A Turlach wrote: G'day Carl, On Mon, 23 Mar 2009 20:11:19 -0400 Carl Witthoft c...@witthoft.com wrote: From: Wacek Kusnierczyk Waclaw.Marcin.Kusnierczyk_at_idi.ntnu.no Date: Sun, 22 Mar 2009 22:58:49 +0100 just for fun, you could do this with multiassignment, e.g., using the (highly experimental and premature!) rvalues: source('http://miscell.googlecode.com/svn/rvalues/rvalues.r') if (TRUE) c(df1, df2) := list(4:8, 9:13) dput(df1) # 4:8 dput(df2) # 9:13 --- Now THAT's what I call an overloaded operator! ^_^ it's not really overloaded, it's *loaded*. if you type a := 1 in an r session without defining '=', r cannot 'find such a function', but it doesn't complain about invalid syntax. so there is the operator, only that it's not operational. But seriously: can someone explain to me what's going on in the rvalues.r code? i think i-the-sinner'd be the right person to ask. i'd suggest to discuss offline, because rvalues is really an experiment, a proof of concept, and as such may not be of interest for wider audience. (it might be that it will be developed into something substantial, but no guarantees.) vQ __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
[R] How to separate huge dataset into chunks
Hello all, Im trying to take a huge dataset (1.5 GB) and separate it into smaller chunks with R. So far I had nothing but problems. I cannot load the whole dataset in R due to memory problems. So, I instead try to load a few (10) lines at a time (with read.table). However, R kept crashing (with no error message) at about the 680 line. This is extremely frustrating. To try to fix this, I used connections with read.table. However, I now get a cryptic error telling me no lines available in input. Is there any way to make this work? Best, Guillaume __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
[R] Which features would you like to see on the crantastic.org community portal?
Hi, As some of you know, one of the R Projects ideas for GSOC 2009 is to expand the crantastic.org portal. Some ideas for what should be done is mentioned in Hadley Wickham's project description [1], others have been briefly mentioned on this mailing list before. Undoubtedly, however, there are many other good ideas out there that could be implemented. Please suggest any ideas you might have for such a package portal. The main focus, as I see it, is to make it as easy as possible to find the package you are looking for, without knowing the name of the package. To facilitate both collection of ideas and voting to show which ideas are most popular, I've setup an account at uservoice.com, available from this URL: http://crantastic.uservoice.com/pages/general . No signup is required to vote and/or add your ideas, so please go ahead. Best regards, Bjørn Arild Mæland Would-be GSOC student [1]: http://www.statistik.lmu.de/~eugster/soc09/#p1 __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
Re: [R] If statement generates two outputs
Berwin A Turlach wrote: G'day Carl, On Mon, 23 Mar 2009 20:11:19 -0400 Carl Witthoft c...@witthoft.com wrote: But seriously: can someone explain to me what's going on in the rvalues.r code? I tried a simple experiment, replacing := with a colec in the code, and of course the line c(df1, df2) colec list(4:8, 9:13) just gives me a syntax error response. Clearly I need a pointer to some documentation about how the colon and equals sign get special treatment somewhere inside R. Not sure why := gets a special treatment, yet another bug?? perhaps because it is not a valid name and, hence, the parser deduces that it is an operator? well, you can't do it with, e.g., ':==', because you'd get a *syntactic* error (while ':=' gives a semantic error): a :== 1 # syntactic error: unexpected '=' in ':=' ':==' = function(a, b) NULL a :== 1 # syntactic error again, of course it's indeed surprising that it works with ':=' but not with, e.g., ':'. and in cases like ':-' you'd in fact use two operators (so an 'overloading' won't work for these): ':-' = function(a, b) a - if(a b) b else 0 2 :- 1 # 2 1 0 -1 # not 1 it's interesting to note that a : b # error: unexpected '' in ':' will tell you what's unexpected, while a :% b # error: unexpected input in 'a :% b' a :_ b # error: unexpected input in 'a :_' will leave you wondering what's wrong there. vQ __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
Re: [R] If statement generates two outputs
Wacek Kusnierczyk wrote: Berwin A Turlach wrote: G'day Carl, On Mon, 23 Mar 2009 20:11:19 -0400 Carl Witthoft c...@witthoft.com wrote: But seriously: can someone explain to me what's going on in the rvalues.r code? I tried a simple experiment, replacing := with a colec in the code, and of course the line c(df1, df2) colec list(4:8, 9:13) just gives me a syntax error response. Clearly I need a pointer to some documentation about how the colon and equals sign get special treatment somewhere inside R. Not sure why := gets a special treatment, yet another bug?? This is probably due to that in the gram.y file : case ':': if (nextchar(':')) { if (nextchar(':')) { yylval = install(:::); return NS_GET_INT; } else { yylval = install(::); return NS_GET; } } if (nextchar('=')) { yylval = install(:=); return LEFT_ASSIGN; } yylval = install(:); return ':'; which gives a meaning to :=, so that parsing x := 2 makes sense. parse( text = x := 2 ) expression(x := 2) attr(,srcfile) text Romain perhaps because it is not a valid name and, hence, the parser deduces that it is an operator? well, you can't do it with, e.g., ':==', because you'd get a *syntactic* error (while ':=' gives a semantic error): a :== 1 # syntactic error: unexpected '=' in ':=' ':==' = function(a, b) NULL a :== 1 # syntactic error again, of course it's indeed surprising that it works with ':=' but not with, e.g., ':'. and in cases like ':-' you'd in fact use two operators (so an 'overloading' won't work for these): ':-' = function(a, b) a - if(a b) b else 0 2 :- 1 # 2 1 0 -1 # not 1 it's interesting to note that a : b # error: unexpected '' in ':' will tell you what's unexpected, while a :% b # error: unexpected input in 'a :% b' a :_ b # error: unexpected input in 'a :_' will leave you wondering what's wrong there. vQ __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code. -- Romain Francois Independent R Consultant +33(0) 6 28 91 30 30 http://romainfrancois.blog.free.fr __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
Re: [R] If statement generates two outputs
Romain Francois wrote: This is probably due to that in the gram.y file : case ':': if (nextchar(':')) { if (nextchar(':')) { yylval = install(:::); return NS_GET_INT; } else { yylval = install(::); return NS_GET; } } if (nextchar('=')) { yylval = install(:=); return LEFT_ASSIGN; } yylval = install(:); return ':'; which gives a meaning to :=, so that parsing x := 2 makes sense. parse( text = x := 2 ) expression(x := 2) attr(,srcfile) text thanks. so it seems to be intentionally parsable, though i wouldn't say that this gives a meaning to ':=' -- the operator has a syntactic category, but no semantics. the syntactic category does not imply any semantics, as in '-' = function(a, b) NULL 1 - a # NULL where '-' is still parsed the original way (as a LEFT_ASSIGN, gram.y again), but has now a completely different semantics. it looks like a bug to me: ':=' is parsed on par with '-' as a LEFT_ASSIGN, but apparently is not backed by any function. it's a zombie. (unless rvalues is used, that is.) vQ __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
Re: [R] If statement generates two outputs
On Tue, 24 Mar 2009, Wacek Kusnierczyk wrote: thanks. so it seems to be intentionally parsable, though i wouldn't say that this gives a meaning to ':=' -- the operator has a syntactic category, but no semantics. the syntactic category does not imply any semantics, as in '-' = function(a, b) NULL 1 - a # NULL where '-' is still parsed the original way (as a LEFT_ASSIGN, gram.y again), but has now a completely different semantics. it looks like a bug to me: ':=' is parsed on par with '-' as a LEFT_ASSIGN, but apparently is not backed by any function. it's a zombie. (unless rvalues is used, that is.) yes, it's a zombie. It used to assign to the R system environment rather than the global workspace (roughly what is the base namespace now). -thomas Thomas Lumley Assoc. Professor, Biostatistics tlum...@u.washington.eduUniversity of Washington, Seattle __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
Re: [R] How to separate huge dataset into chunks
On Tue, 24 Mar 2009, Guillaume Filteau wrote: Hello all, Im trying to take a huge dataset (1.5 GB) and separate it into smaller chunks with R. So far I had nothing but problems. I cannot load the whole dataset in R due to memory problems. So, I instead try to load a few (10) lines at a time (with read.table). However, R kept crashing (with no error message) at about the 680 line. This is extremely frustrating. To try to fix this, I used connections with read.table. However, I now get a cryptic error telling me no lines available in input. Is there any way to make this work? There might be an error in line 42 of your script. Or somewhere else. The error message is cryptically saying that there were no lines of text available in the input connection, so presumably the connection wasn't pointed at your file correctly. It's hard to guess without seeing what you are doing, but conn - file(mybigfile, open=r) chunk- read.table(conn, header=TRUE, nrows=1) nms - names(chunk) while(length(chunk)==1){ chunk-read.table(conn, nrows=1,col.names=nms) ## do something to the chunk } close(conn) should work. This sort of thing certainly does work routinely. It's probably not worth reading 100,000 lines at a time unless your computer has a lot of memory. Reducing the chunk size to 10,000 shouldn't introduce much extra overhead and may well increase the speed by reducing memory use. -thomas Thomas Lumley Assoc. Professor, Biostatistics tlum...@u.washington.eduUniversity of Washington, Seattle __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
Re: [R] If statement generates two outputs
Thomas Lumley wrote: On Tue, 24 Mar 2009, Wacek Kusnierczyk wrote: thanks. so it seems to be intentionally parsable, though i wouldn't say that this gives a meaning to ':=' -- the operator has a syntactic category, but no semantics. the syntactic category does not imply any semantics, as in '-' = function(a, b) NULL 1 - a # NULL where '-' is still parsed the original way (as a LEFT_ASSIGN, gram.y again), but has now a completely different semantics. it looks like a bug to me: ':=' is parsed on par with '-' as a LEFT_ASSIGN, but apparently is not backed by any function. it's a zombie. (unless rvalues is used, that is.) yes, it's a zombie. It used to assign to the R system environment rather than the global workspace (roughly what is the base namespace now). thanks for the explanation. for the sake of rvalues, please do not fix this bug. i find it useful to avoid messing with = and -. vQ __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
Re: [R] If statement generates two outputs
On Tue, 24 Mar 2009, Wacek Kusnierczyk wrote: thanks for the explanation. for the sake of rvalues, please do not fix this bug. i find it useful to avoid messing with = and -. If you insist on calling it a bug, the chances of its getting fixed are higher. -thomas Thomas Lumley Assoc. Professor, Biostatistics tlum...@u.washington.eduUniversity of Washington, Seattle __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
[R] Random sampling based on the observations
Hello!I am having a problem with Random sampling in R. I have used a syntax: mydata.sub=sample(mydata,7,replace=FALSE,prob=NULL) which allows me to choose a random sample based on the variables(correct me if I am wrong!). Suppose I have 10 variable and if I use the above mentioned command then it will choose 7 variables out of the 10 randomly. My problem is that I want to have a random sample which is not based on the variables but on the values of the variables that is the random sample will be based on the observations. It will be great if someone can help me out me out with a proper syntax. Thanks in Advance. -- View this message in context: http://www.nabble.com/Random-sampling-based-on-the-observations-tp22673975p22673975.html Sent from the R help mailing list archive at Nabble.com. __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
[R] Unit root
I am confused by obtaining different results when testing for unit root when using different packages. I have 2625 price entries for which I want to determine whether they exhibit unit root. First I test using adf.test from tseries package by running: adf.test(P, k=30) Augmented Dickey-Fuller Test data: P Dickey-Fuller = -4.685, Lag order = 30, p-value = 0.01 alternative hypothesis: stationary Warning message: In adf.test(P, k = 30) : p-value smaller than printed p-value But adf.test includes a time trend that I wan to omit, which I do not know if it is possible. Thus I have to run ADF .test from uroot package and obtain the following: ADF.test(Plevel, itsd=c(1,1,c(0)),regvar=0, selectlags=list(Pmax=30)) - -- - -- Augmented Dickey Fuller test - -- - -- Null hypothesis: Unit root. Alternative hypothesis: Stationarity. ADF statistic: Estimate Std. Error t value Pr(|t|) adf.reg -0.326 0.015 -21.881 0.01 Lag orders: 30 Number of available observations: 2594 Warning message: In interpolpval(code = code, stat = adfreg[, 3], N = N) : p-value is smaller than printed p-value The results are dramatically different. Even more interesting is when I include the option for the program to select the number of lags: ADF.test(Plevel, itsd=c(1,1,c(0)),regvar=0, selectlags=list(mode='signf', Pmax=NULL)) - -- - -- Augmented Dickey Fuller test - -- - -- Null hypothesis: Unit root. Alternative hypothesis: Stationarity. ADF statistic: Estimate Std. Error t value Pr(|t|) adf.reg -0.079 0.017 -4.727 0.01 Lag orders: 1 2 3 4 5 6 9 10 11 12 13 14 15 16 17 18 19 20 21 23 24 25 26 27 28 31 32 33 34 Number of available observations: 2590 Warning message: In interpolpval(code = code, stat = adfreg[, 3], N = N) : p-value is smaller than printed p-value Can someone please explain these differences. Many thanks, Jurica Brajkovic University of Southampton __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
[R] cross-validation
I have reviewed all the scripts that appear http://cran.es.r-project.org/ and I cann´t find any suitable for cross-validation with a model of the form y = aX^(b). exp(cZ). Please can someone help me? Thanks, a lot of!! -- View this message in context: http://www.nabble.com/cross-validation-tp22674165p22674165.html Sent from the R help mailing list archive at Nabble.com. __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
Re: [R] help: what are the basis functions in {mgcv}: gam?
Thanks for Andrew Robinson's suggestion. I am sorry that I have been looking for the book Wood (2006) Generalized Additive Models: Introduction with R for a long time in my univerity and book stores, but I failed to find one. I think it may take a long time to buy one from the Internet, and we are required to submit the master thesis soon... Could any one help me if you know other references or have knowledge about this?? I will be very very thankful. Sincerely yours, Olivia oliviax wrote: I am writing my thesis with the function gam(), with the package {mgcv}. My command is: gam(y~s(x1,bs=cr)+s(x2, bs=cr)). I need help to know what are the default basis funcitons for gam. I have not found any detailed reference for this. Can anyone help me with this?? -- View this message in context: http://www.nabble.com/help%3A-what-are-the-basis-functions-in-%7Bmgcv%7D%3A-gam--tp22673295p22674337.html Sent from the R help mailing list archive at Nabble.com. __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
[R] Change teh datatype from factor to double
Hi all, I want to read a .txt dataset, but when I test the type, some of the data is a factor. How can I avoid them to get a factor or how can I unfactor them without loosing their values? Thanks, Max -- View this message in context: http://www.nabble.com/Change-teh-datatype-from-factor-to-double-tp22675854p22675854.html Sent from the R help mailing list archive at Nabble.com. __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
Re: [R] Random sampling based on the observations
On Tuesday 24 March 2009, you wrote: Hello!I am having a problem with Random sampling in R. I have used a syntax: mydata.sub=sample(mydata,7,replace=FALSE,prob=NULL) which allows me to choose a random sample based on the variables(correct me if I am wrong!). Actually, no. You are sampling from a vector, and where you're using the sampled values (on the rows or on the variables) is up to you. Let's say we have a dataset with 100 cases and 10 variables: Case 1: mydata.sub - mydata[ , sample(10, 7)] This will sample 7 variables out of 10. Case 2: mydata.sub - mydata[sample(100, 10), ] This will sample 10 cases out of 100. Suppose I have 10 variable and if I use the above mentioned command then it will choose 7 variables out of the 10 randomly. My problem is that I want to have a random sample which is not based on the variables but on the values of the variables that is the random sample will be based on the observations. It will be great if someone can help me out me out with a proper syntax. Thanks in Advance. I think you need to read the help for: ?[ and most probably one of the introductory books for R. I hope this helps, Adrian -- Adrian Dusa Romanian Social Data Archive 1, Schitu Magureanu Bd. 050025 Bucharest sector 5 Romania Tel.:+40 21 3126618 \ +40 21 3120210 / int.101 Fax: +40 21 3158391 [[alternative HTML version deleted]] __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
Re: [R] confidence interval or error of x intercept of a linear
On 24-Mar-09 03:31:32, Kevin J Emerson wrote: Hello all, This is something that I am sure has a really suave solution in R, but I can't quite figure out the best (or even a basic) way to do it. I have a simple linear regression that is fit with lm for which I would like to estimate the x intercept with some measure of error around it (confidence interval). In biology, there is the concept of a developmental zero - a temperature under which development will not happen. This is often estimated by extrapolation of a curve of developmental rate as a function of temperature. This developmental zero is generally reported without error. I intend to change this! There has to be some way to assign error to this term, I just have yet to figure it out. Now, it is simple enough to calculate the x-intercept itself ( - intercept / slope ), but it is a whole separate process to generate the confidence interval of it. I can't figure out how to propagate the error of the slope and intercept into the ratio of the two. The option option I have tried to figure out is to use the predict function to look for where the confidence intervals cross the axis but this hasn't been too fruitful either. I would greatly appreciate any insight you may be able to share. Cheers, Kevin Here is a small representative sample of some of my data where Dev.Rate ~ Temperature. The difficulty with the situation you describe is that you are up against what is known as the Calibration Problem in Statistics. Essentially, the difficulty is that in the theory of the linear regression there is sufficient probability for the slope to be very close to zero -- and hence that the X-intercept maybe very far out to the left or the right -- that the whole dconcept of Standard error ceases to exist. Even the expected position of the intercept does not exist. And this is true regardless of the data (the one exception would be where it is absolutely certain that the data will lie exactly on a straight line). This has been addressed a number of times, and controversally, in the statistical literature. One approach which I like (having thought of it myself :)) is the use of likelihood-based confidence intervals. Given a linear regression Y = a + b*X + E (where the error E has N(0, sig^2) distribution), suppose you want to estimate the value X0 of X for which Y = Y0, a given value (in your case Y0 = 0). For simplicity, measure X and Y from their means sum(X)/N and sum(Y)/N. The approach is based on comparing the likelihoods [A] for unresticted ML estimation of a, b and sig -- a.hat, b.hat, sig.hat (where a.hat = 0 because of the origins of X and Y) [B] for ML estimation assuming a particular value X1 for X0 -- a.tilde, b.tilde, sig.tilde where [A] a.hat = 0 (as above), b.hat = (sum(X*Y))/(sum(X^2) X0.hat= Y0/b.hat [ = -mean(Y)/b.hat in your case ] sig.hat^2 = (sum(Y - b.hat*X)^2)/(N+1) [B] a.tilde = (sum(X^2) - X0*sum(X*Y))/D b.tilde = ((N+1)*sum(X*Y) + N*X1*Y0)/D sig.hat.tilde^2 = (sum((Y - a.tilde - b.tilde*X)^2) + (Y0 - a.tilde - b.tilde*X1)^2)/(N+1) where D = (N+1)*sum(X^2 + N*X1^2 Then let R(X1) = (sig.hat^2)/(sig.tilde^2) A confidence interval for X0 is the set of values of X1 such that R(X1) R0 say, where Prob(R(X0)R0) = P, the desired confidence level, when X0 is the true value. It can be established that (N-2)*(1 - R(X0))/R(X0) has the F distribution with 1 and (N-1) degrees of freedom. Since this is independent of X0, the resulting set of values of X1 constitute a confidence interval. This was described in Harding, E.F. (1986). Modelling: the classical approach. The Statistician vol. 35, pp. 115-134 (see pages 123-126) and has been later referred to by P.J. Brown (thought I don't have the references to hand just now). When I have time for it (not today) I'll see if I can implement this neatly in R. It's basically a question of solving (N-2)*(1 - R(X0))/R(X0) = qf(P,1,(N-1)) for X0 (two solutions, maybe one, if any exist). However, it is quite possible that no solution exists (depending on P), so that the confidence interval would then be (-inf,+inf); or, when only one exists, it will be either (-inf,X0) or (X0,inf). These possibilities of infinite intervals are directly related to the possibility that, at significance level alpha = (1-P), the estimated slope may not differ significantly from 0. Maybe more later! Ted. E-Mail: (Ted Harding) ted.hard...@manchester.ac.uk Fax-to-email: +44 (0)870 094 0861 Date: 24-Mar-09 Time: 10:04:30 -- XFMail -- __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and
Re: [R] If statement generates two outputs
Thomas Lumley wrote: On Tue, 24 Mar 2009, Wacek Kusnierczyk wrote: thanks for the explanation. for the sake of rvalues, please do not fix this bug. i find it useful to avoid messing with = and -. If you insist on calling it a bug, the chances of its getting fixed are higher. no no, it's *NOT* a b(...)! vQ __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
Re: [R] help: what are the basis functions in {mgcv}: gam?
If you can't get hold of the book, try appendix A of http://www.maths.bath.ac.uk/~sw283/simon/papers/psm.pdf -- what's described there is the cr basis best, Simon On Tuesday 24 March 2009 05:01, oliviax wrote: Thanks for Andrew Robinson's suggestion. I am sorry that I have been looking for the book Wood (2006) Generalized Additive Models: Introduction with R for a long time in my univerity and book stores, but I failed to find one. I think it may take a long time to buy one from the Internet, and we are required to submit the master thesis soon... Could any one help me if you know other references or have knowledge about this?? I will be very very thankful. Sincerely yours, Olivia oliviax wrote: I am writing my thesis with the function gam(), with the package {mgcv}. My command is: gam(y~s(x1,bs=cr)+s(x2, bs=cr)). I need help to know what are the default basis funcitons for gam. I have not found any detailed reference for this. Can anyone help me with this?? -- Simon Wood, Mathematical Sciences, University of Bath, Bath, BA2 7AY UK +44 1225 386603 www.maths.bath.ac.uk/~sw283 __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
[R] install.package(TinnR) - there is no package called 'TinnR'
I have troubles make TinnR 2.2.0.2 work, it seems that the dependency on the package TinnR that cannot be found (I tried also manual downloads, but I cannot find the package anywhere on any CRAN mirror). I even set a default cran mirror in the Rprofile.site file, so that the later command can find it: # check necesary packages necessary = c('TinnR', 'svSocket') installed = necessary %in% installed.packages()[, 'Package'] if (length(necessary[!installed]) =1) install.packages(necessary[!installed], dep=T). No luck. Even manually issuing the comand in Rterm fails, package ‘TinnR’ is not available. Any idea how I could make my TinnR work? I googled extensively, but without luck... Thanks Martin __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
[R] r online
Hi, I'd like to execute simple commands and functions in R through a website, is there any service like this somewhere? I only found http://www.osvisions.com/r-online/ but it does not work (last update 2003) and the links to releated websites only give errors (if I calculate 7+3). Thanks for help hints, Thomas __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
Re: [R] Legend containing maths symbol and values of variables
Try this: L - list(bquote(Up ( = .(threshold) ~ )), Normal, Down, NA) legend(top, leg = L) On Tue, Mar 24, 2009 at 2:52 AM, Daren Tan darenta...@gmail.com wrote: I tried sprintf and paste, which solves one of my problem i.e. replacing the variable name by its value. However, = is not renderend correctly as the inequality symbol. On Tue, Mar 24, 2009 at 12:24 PM, Gabor Grothendieck ggrothendi...@gmail.com wrote: For the legend argument try this: leg = as.expression(c(sprintf(Up (= %d), threshold), Normal, Down, NA)) or use paste in place of sprintf. On Mon, Mar 23, 2009 at 11:53 PM, Daren Tan darenta...@gmail.com wrote: I need to have the maths symbol for = in the legend, and to substitute threshold variable with its value. Somehow, various attempts weren't successful. Please help. threshold - 0.5 plot(NA, xlab=, ylab=, main=, axes=F, xlim=c(0,1), ylim=c(0,1), xaxs=i, yaxs=i) legend(x=0, y=1, fill=c(orange, white, green, gray90), cex=0.8, pt.cex=1.8, x.intersp=0.6, bg = white, legend=c(expression(Up ( = threshold )), Normal, Down, NA), bty = n) __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code. __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
Re: [R] Legend containing maths symbol and values of variables
So what about threshold - 0.5 plot(NA, xlab=, ylab=, main=, axes=F, xlim=c(0,1), ylim=c(0,1), xaxs=i, yaxs=i) legend1 - substitute(Up ( * phantom() = threshold * ), list(threshold=threshold)) legend(x=0, y=1, fill=c(orange, white, green, gray90), cex=0.8, pt.cex=1.8, x.intersp=0.6, bg = white, bty = n, legend = do.call(expression, list(legend1, Normal, Down, NA))) Daren Tan wrote: I tried sprintf and paste, which solves one of my problem i.e. replacing the variable name by its value. However, = is not renderend correctly as the inequality symbol. On Tue, Mar 24, 2009 at 12:24 PM, Gabor Grothendieck ggrothendi...@gmail.com wrote: For the legend argument try this: leg = as.expression(c(sprintf(Up (= %d), threshold), Normal, Down, NA)) or use paste in place of sprintf. On Mon, Mar 23, 2009 at 11:53 PM, Daren Tan darenta...@gmail.com wrote: I need to have the maths symbol for = in the legend, and to substitute threshold variable with its value. Somehow, various attempts weren't successful. Please help. threshold - 0.5 plot(NA, xlab=, ylab=, main=, axes=F, xlim=c(0,1), ylim=c(0,1), xaxs=i, yaxs=i) legend(x=0, y=1, fill=c(orange, white, green, gray90), cex=0.8, pt.cex=1.8, x.intersp=0.6, bg = white, legend=c(expression(Up ( = threshold )), Normal, Down, NA), bty = n) __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code. __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code. __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
[R] How to find the path or the current file?
Dear useRs, I have a collection of source file and some of these call others. The files are distribute among a number of directories, and to know how to call some other file they need to know what file is currently executed. As example, I have a file 'search.R' located in directory 'bin' which needs to access the file 'terms.conf' located in the directory 'conf', a sibling of 'bin'. I can have somethings like readLines('../conf/terms.conf') in search.R, but this work only if search.R is executed from bin, when getwd is 'bin'. But when search.R calls from the parent as bin/search.R or any other derectory then R complains that it could not find the file '../conf/terms.conf'. So my questions is: how can the file search.R, when executied, discover its own location and load terms.conf from location of search.R/../conf/terms.conf? the location of search.R can be unrelated to the current directory. Mvh. Marie [[alternative HTML version deleted]] __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
[R] Variogram with Gstat
Dear all can you help me? i have this problem: i have a dataset in a text file in a matrix of 3 columns: x, y, z where x and y are the coordinates and Z are the mesurements. How can i do a variogram with R? __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
Re: [R] read in large data file (tsv) with inline filter?
On Mon, Mar 23, 2009 at 5:53 PM, David Reiss dre...@systemsbiology.org wrote: I have a very large tab-delimited file, too big to store in memory via readLines() or read.delim(). Turns out I only need a few hundred of those lines to be read in. If it were not so large, I could read the entire file in and grep the lines I need. For such a large file; many calls to read.delim() with incrementing skip and nrows parameters, followed by grep() calls is very slow. I am aware of possibilities via SQLite; I would prefer to not use that in this case. Why the restriction? Using sqldf with sqlite its only two R statements. The first statement defines the name of the file and the second statement defines what you want to extract from it and its format. First create a sample file using built in data frame BOD and lets specify tab delimiters. A header, i.e. col.names = TRUE, is the default for write.table: # create tab delimited test file with headers write.table(BOD, file = myfile.dat, sep = \t) # now read in only those records satisfying a condition library(sqldf) # here are the two statements myfile - file(myfile.dat) DF - sqldf(select * from myfile where demand 10 or demand 15, file.format = list(sep = \t)) See examples on the home page http://sqldf.googlecode.com and see ?sqldf for info on the file.format argument in case your format differs. __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
Re: [R] How to find the path or the current file?
On 24/03/2009 7:16 AM, Marie Sivertsen wrote: Dear useRs, I have a collection of source file and some of these call others. The files are distribute among a number of directories, and to know how to call some other file they need to know what file is currently executed. As example, I have a file 'search.R' located in directory 'bin' which needs to access the file 'terms.conf' located in the directory 'conf', a sibling of 'bin'. I can have somethings like readLines('../conf/terms.conf') in search.R, but this work only if search.R is executed from bin, when getwd is 'bin'. But when search.R calls from the parent as bin/search.R or any other derectory then R complains that it could not find the file '../conf/terms.conf'. So my questions is: how can the file search.R, when executied, discover its own location and load terms.conf from location of search.R/../conf/terms.conf? the location of search.R can be unrelated to the current directory. In general it can't. Since source() can work on a connection and a connection doesn't have to be a file, there may not be a location. You could write your own Source function, something like this: filenamestack - c() Source - function(filename, ...) { # push the new filename filenamestack - c(filename, filenamestack) # on exit pop it off the stack on.exit(filenamestack - filenamestack[-1]) source(filename, ...) } and then examine filenamestack[1] to find the name of the file currently being sourced. (But Source() won't work on connections, only on filenames.) Duncan Murdoch __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
Re: [R] Legend containing maths symbol and values of variables
that should have been: L - list(bquote(Up ( = .(threshold) ~ )), Normal, Down, NA) legend(top, leg = as.expression(L)) On Tue, Mar 24, 2009 at 7:18 AM, Gabor Grothendieck ggrothendi...@gmail.com wrote: Try this: L - list(bquote(Up ( = .(threshold) ~ )), Normal, Down, NA) legend(top, leg = L) On Tue, Mar 24, 2009 at 2:52 AM, Daren Tan darenta...@gmail.com wrote: I tried sprintf and paste, which solves one of my problem i.e. replacing the variable name by its value. However, = is not renderend correctly as the inequality symbol. On Tue, Mar 24, 2009 at 12:24 PM, Gabor Grothendieck ggrothendi...@gmail.com wrote: For the legend argument try this: leg = as.expression(c(sprintf(Up (= %d), threshold), Normal, Down, NA)) or use paste in place of sprintf. On Mon, Mar 23, 2009 at 11:53 PM, Daren Tan darenta...@gmail.com wrote: I need to have the maths symbol for = in the legend, and to substitute threshold variable with its value. Somehow, various attempts weren't successful. Please help. threshold - 0.5 plot(NA, xlab=, ylab=, main=, axes=F, xlim=c(0,1), ylim=c(0,1), xaxs=i, yaxs=i) legend(x=0, y=1, fill=c(orange, white, green, gray90), cex=0.8, pt.cex=1.8, x.intersp=0.6, bg = white, legend=c(expression(Up ( = threshold )), Normal, Down, NA), bty = n) __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code. __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
Re: [R] r online
try: http://bayes.math.montana.edu/Rweb/Rweb.general.html Gerhard Thomas Steiner schrieb am 24.03.2009 12:06: Hi, I'd like to execute simple commands and functions in R through a website, is there any service like this somewhere? I only found http://www.osvisions.com/r-online/ but it does not work (last update 2003) and the links to releated websites only give errors (if I calculate 7+3). Thanks for help hints, Thomas __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code. -- Gerhard Schön Department of Medical Biometry and Epidemiology University Medical Center Hamburg-Eppendorf Martinistr. 52, building W34 Phone: +49(40) 7410 57458 Fax: +49(40) 7410 57790 Web: www.uke.de/imbe -- Pflichtangaben gemäß Gesetz über elektronische Handelsregister und Genossenschaftsregister sowie das Unternehmensregister (EHUG): Universitätsklinikum Hamburg-Eppendorf Körperschaft des öffentlichen Rechts Gerichtsstand: Hamburg Vorstandsmitglieder: Prof. Dr. Jörg F. Debatin (Vorsitzender) Dr. Alexander Kirstein Ricarda Klein Prof. Dr. Dr. Uwe Koch-Gromus __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
Re: [R] Change teh datatype from factor to double
?read.table Consult the help file for the parameters: as.is =or stringsAsFactors = -- David Winsemius On Mar 24, 2009, at 4:22 AM, Maxl18 wrote: Hi all, I want to read a .txt dataset, but when I test the type, some of the data is a factor. How can I avoid them to get a factor or how can I unfactor them without loosing their values? Thanks, Max -- View this message in context: http://www.nabble.com/Change-teh-datatype-from-factor-to-double-tp22675854p22675854.html Sent from the R help mailing list archive at Nabble.com. __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code. David Winsemius, MD Heritage Laboratories West Hartford, CT __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
Re: [R] r online
On 24 March 2009 at 12:06, Thomas Steiner wrote: | Hi, | I'd like to execute simple commands and functions in R through a | website, is there any service like this somewhere? | I only found http://www.osvisions.com/r-online/ but it does not work | (last update 2003) and the links to releated websites only give errors | (if I calculate 7+3). | Thanks for help hints, Please read the R FAQ which has an entire section devoted to this that I include below, copied and pasted from the txt version of the R FAQ. Personally, I'd go with Rpad. Dirk 4 R Web Interfaces ** *Rweb* is developed and maintained by Jeff Banfield j...@math.montana.edu. The Rweb Home Page (http://www.math.montana.edu/Rweb/) provides access to all three versions of Rweb--a simple text entry form that returns output and graphs, a more sophisticated Javascript version that provides a multiple window environment, and a set of point and click modules that are useful for introductory statistics courses and require no knowledge of the R language. All of the Rweb versions can analyze Web accessible datasets if a URL is provided. The paper Rweb: Web-based Statistical Analysis, providing a detailed explanation of the different versions of Rweb and an overview of how Rweb works, was published in the Journal of Statistical Software (`http://www.jstatsoft.org/v04/i01/'). Ulf Bartel u...@cs.tu-berlin.de has developed *R-Online*, a simple on-line programming environment for R which intends to make the first steps in statistical programming with R (especially with time series) as easy as possible. There is no need for a local installation since the only requirement for the user is a JavaScript capable browser. See `http://osvisions.com/r-online/' for more information. *Rcgi* is a CGI WWW interface to R by MJ Ray m...@dsl.pipex.com. It had the ability to use embedded code: you could mix user input and code, allowing the HTML author to do anything from load in data sets to enter most of the commands for users without writing CGI scripts. Graphical output was possible in PostScript or GIF formats and the executed code was presented to the user for revision. However, it is not clear if the project is still active. Currently, a modified version of *Rcgi* by Mai Zhou m...@ms.uky.edu (actually, two versions: one with (bitmap) graphics and one without) as well as the original code are available from `http://www.ms.uky.edu/~statweb/'. CGI-based web access to R is also provided at `http://hermes.sdu.dk/cgi-bin/go/'. There are many additional examples of web interfaces to R which basically allow to submit R code to a remote server, see for example the collection of links available from `http://biostat.mc.vanderbilt.edu/twiki/bin/view/Main/StatCompCourse'. David Firth (http://www.warwick.ac.uk/go/dfirth) has written *CGIwithR*, an R add-on package available from CRAN. It provides some simple extensions to R to facilitate running R scripts through the CGI interface to a web server, and allows submission of data using both GET and POST methods. It is easily installed using Apache under Linux and in principle should run on any platform that supports R and a web server provided that the installer has the necessary security permissions. David's paper CGIwithR: Facilities for Processing Web Forms Using R was published in the Journal of Statistical Software (`http://www.jstatsoft.org/v08/i10/'). The package is now maintained by Duncan Temple Lang dun...@wald.ucdavis.edu and has a web page at `http://www.omegahat.org/CGIwithR/'. Rpad (http://www.rpad.org/Rpad), developed and actively maintained by Tom Short, provides a sophisticated environment which combines some of the features of the previous approaches with quite a bit of Javascript, allowing for a GUI-like behavior (with sortable tables, clickable graphics, editable output), etc. Jeff Horner is working on the R/Apache Integration Project which embeds the R interpreter inside Apache 2 (and beyond). A tutorial and presentation are available from the project web page at `http://biostat.mc.vanderbilt.edu/twiki/bin/view/Main/RApacheProject'. Rserve (http://stats.math.uni-augsburg.de/Rserve/) is a project actively developed by Simon Urbanek. It implements a TCP/IP server which allows other programs to use facilities of R. Clients are available from the web site for Java and C++ (and could be written for other languages that support TCP/IP sockets). OpenStatServer (http://openstatserver.org/index.html) is being developed by a team lead by Greg Warnes; it aims to provide clean access to computational modules defined in a variety of computational environments (R, SAS, Matlab, etc) via a single well-defined client interface and to turn computational services into web services. Two projects use PHP to provide a web interface to R. R_PHP_Online (http://steve-chen.net/R_PHP/) by Steve Chen (though it is unclear if this project is still active) is somewhat
Re: [R] How to find the path or the current file?
See: https://stat.ethz.ch/pipermail/r-help/2009-January/184745.html On Tue, Mar 24, 2009 at 7:16 AM, Marie Sivertsen mariesiv...@gmail.com wrote: Dear useRs, I have a collection of source file and some of these call others. The files are distribute among a number of directories, and to know how to call some other file they need to know what file is currently executed. As example, I have a file 'search.R' located in directory 'bin' which needs to access the file 'terms.conf' located in the directory 'conf', a sibling of 'bin'. I can have somethings like readLines('../conf/terms.conf') in search.R, but this work only if search.R is executed from bin, when getwd is 'bin'. But when search.R calls from the parent as bin/search.R or any other derectory then R complains that it could not find the file '../conf/terms.conf'. So my questions is: how can the file search.R, when executied, discover its own location and load terms.conf from location of search.R/../conf/terms.conf? the location of search.R can be unrelated to the current directory. Mvh. Marie [[alternative HTML version deleted]] __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code. __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
Re: [R] Legend containing maths symbol and values of variables
Thanks, that works beautifully. Without your help, I will be struggling for a long time. On Tue, Mar 24, 2009 at 7:46 PM, Gabor Grothendieck ggrothendi...@gmail.com wrote: that should have been: L - list(bquote(Up ( = .(threshold) ~ )), Normal, Down, NA) legend(top, leg = as.expression(L)) On Tue, Mar 24, 2009 at 7:18 AM, Gabor Grothendieck ggrothendi...@gmail.com wrote: Try this: L - list(bquote(Up ( = .(threshold) ~ )), Normal, Down, NA) legend(top, leg = L) On Tue, Mar 24, 2009 at 2:52 AM, Daren Tan darenta...@gmail.com wrote: I tried sprintf and paste, which solves one of my problem i.e. replacing the variable name by its value. However, = is not renderend correctly as the inequality symbol. On Tue, Mar 24, 2009 at 12:24 PM, Gabor Grothendieck ggrothendi...@gmail.com wrote: For the legend argument try this: leg = as.expression(c(sprintf(Up (= %d), threshold), Normal, Down, NA)) or use paste in place of sprintf. On Mon, Mar 23, 2009 at 11:53 PM, Daren Tan darenta...@gmail.com wrote: I need to have the maths symbol for = in the legend, and to substitute threshold variable with its value. Somehow, various attempts weren't successful. Please help. threshold - 0.5 plot(NA, xlab=, ylab=, main=, axes=F, xlim=c(0,1), ylim=c(0,1), xaxs=i, yaxs=i) legend(x=0, y=1, fill=c(orange, white, green, gray90), cex=0.8, pt.cex=1.8, x.intersp=0.6, bg = white, legend=c(expression(Up ( = threshold )), Normal, Down, NA), bty = n) __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code. __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
Re: [R] read in large data file (tsv) with inline filter?
Hi David, On 23 March 2009 at 15:09, Dylan Beaudette wrote: | On Monday 23 March 2009, David Reiss wrote: | I have a very large tab-delimited file, too big to store in memory via | readLines() or read.delim(). Turns out I only need a few hundred of those | lines to be read in. If it were not so large, I could read the entire file | in and grep the lines I need. For such a large file; many calls to | read.delim() with incrementing skip and nrows parameters, followed by | grep() calls is very slow. I am aware of possibilities via SQLite; I would | prefer to not use that in this case. | | My question is...Is there a function for efficiently reading in a file | along the lines of read.delim(), which allows me to specify a filter (via | grep or something else) that tells the function to only read in certain | lines that match? | | If not, I would *love* to see a filter parameter added as an option to | read.delim() and/or readLines(). | | How about pre-filtering before loading the data into R: | | grep -E 'your pattern here' your_file_here your_filtered_file | | alternatively if you need to search in fields, see 'awk', and 'cut', or if you | need to delete things see 'tr'. | | These tools come with any unix-like OS, and you can probably get them on | windows without much effort. Also note that read.delim() and friends all read from connections, and 'piped expressions' (in the Unix shell command sense) can provide a source. That way you can build an ad-hoc filter extension by running readLines() over a pipe() connection. Consider this trivial example of grepping out Section headers from the R FAQ. We get everything double because of the Table of Contents and the actual section headers: R readLines( pipe(awk '/^[0-9+] / {print $1, $2, $3}' src/debian/R/R-alpha.20090320/doc/FAQ) ) [1] 1 Introduction 2 R Basics 3 R and 4 R Web [5] 5 R Add-On 6 R and 7 R Miscellanea 8 R Programming [9] 9 R Bugs1 Introduction 2 R Basics 3 R and [13] 4 R Web 5 R Add-On 6 R and 7 R Miscellanea [17] 8 R Programming 9 R Bugs R The regexp is simply 'digits at start of line followed by space' which skips subsections like 1.1, 1.2, ... Hth, Dirk -- Three out of two people have difficulties with fractions. __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
Re: [R] mvpart error
On Sun, 2009-03-22 at 22:45 -0400, Josh Stumpf wrote: Hello all, When attempting a classification tree using mvpart, I get the following error: thesis2.mvp=mvpart(bat_sp~., data=alltrees.df) Error in all(keep) : unused argument(s) (c(TRUE, TRUE, TRUE, TRUE, TRUE, TRUE, TRUE, TRUE, TRUE, TRUE, TRUE, TRUE, TRUE, TRUE, TRUE, TRUE, TRUE, TRUE, TRUE, TRUE, TRUE, TRUE, TRUE, TRUE, TRUE, TRUE, TRUE, TRUE, TRUE, TRUE, TRUE, TRUE, TRUE, TRUE, TRUE, TRUE, TRUE, TRUE, TRUE, TRUE, TRUE, TRUE, TRUE, TRUE, TRUE, TRUE, TRUE, TRUE, TRUE, TRUE, TRUE, TRUE, TRUE, TRUE, TRUE, TRUE, TRUE, TRUE, TRUE, TRUE, TRUE, TRUE, TRUE, TRUE, TRUE, TRUE, TRUE, TRUE, TRUE, TRUE, TRUE, TRUE, TRUE, TRUE, TRUE, TRUE, TRUE, TRUE)) bat_sp is an unordered categorical variable That looks wrong for a start. mvpart is an extension to the rpart routines to allow *multivariate* recursive partitioning. You'd be better off just using rpart directly. Have you tried that (i.e. require(rpart) in a clean session, not require(mvpart) )? Does it work then? , and the predictors are a mixture of categorical and continuous variables. I had run the algorithm successfully in the past (about 1.5 years ago) on a preliminary subset of the same dataset using a previous version of R The current system is R 2.8.1 running under Ubuntu Jaunty. Any ideas as to the cause? You've not given us much to go on. Please provide either the data (privately; I promise to use it only to work through this issue and delete immediately thereafter) or (to the list) the output from: str(alltrees.df) I tried to replicate your data and it ran fine in the version of mvpart on my linux box, so seeing what your data looks like may help. Also provide the results of traceback() called immediately after you get the error, eg: thesis2.mvp=mvpart(bat_sp~., data=alltrees.df) Error in all(keep) : unused argument(s) (c(TRUE, TRUE, TRUE, TRUE, TRUE, TRUE, TRUE, TRUE, TRUE, TRUE, TRUE, TRUE, TRUE, TRUE, TRUE, TRUE, TRUE, TRUE, TRUE, TRUE, TRUE, TRUE, TRUE, TRUE, TRUE, TRUE, TRUE, TRUE, TRUE, TRUE, TRUE, TRUE, TRUE, TRUE, TRUE, TRUE, TRUE, TRUE, TRUE, TRUE, TRUE, TRUE, TRUE, TRUE, TRUE, TRUE, TRUE, TRUE, TRUE, TRUE, TRUE, TRUE, TRUE, TRUE, TRUE, TRUE, TRUE, TRUE, TRUE, TRUE, TRUE, TRUE, TRUE, TRUE, TRUE, TRUE, TRUE, TRUE, TRUE, TRUE, TRUE, TRUE, TRUE, TRUE, TRUE, TRUE, TRUE, TRUE)) traceback() I can't find a call to 'all(keep)' in either the mvpart() or rpart() functions, so without knowing where the error occurred or the means to replicate exactly the error, our hands are tied behind our backs somewhat. Finally, send the output from sessionInfo() so we can see what versions of software you are using. HTH Josh Stumpf Eastern Michigan University [[alternative HTML version deleted]] __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code. -- %~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~% Dr. Gavin Simpson [t] +44 (0)20 7679 0522 ECRC, UCL Geography, [f] +44 (0)20 7679 0565 Pearson Building, [e] gavin.simpsonATNOSPAMucl.ac.uk Gower Street, London [w] http://www.ucl.ac.uk/~ucfagls/ UK. WC1E 6BT. [w] http://www.freshwaters.org.uk %~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~% __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
Re: [R] install.package(TinnR) - there is no package called 'TinnR'
Tinn-R is not an R package. It is a standalone text editor: http://www.lmgtfy.com/?q=tinn-r -- David Winsemius On Mar 24, 2009, at 7:05 AM, Martin Tomko wrote: I have troubles make TinnR 2.2.0.2 work, it seems that the dependency on the package TinnR that cannot be found (I tried also manual downloads, but I cannot find the package anywhere on any CRAN mirror). I even set a default cran mirror in the Rprofile.site file, so that the later command can find it: # check necesary packages necessary = c('TinnR', 'svSocket') installed = necessary %in% installed.packages()[, 'Package'] if (length(necessary[!installed]) =1) install.packages(necessary[!installed], dep=T). No luck. Even manually issuing the comand in Rterm fails, package ‘TinnR’ is not available. Any idea how I could make my TinnR work? I googled extensively, but without luck... Thanks Martin __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code. David Winsemius, MD Heritage Laboratories West Hartford, CT __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
Re: [R] install.package(TinnR) - there is no package called 'TinnR'
David, that is not helpful. I KNOW that TinnR is a standalone editor. If you had a look at the Rprofile.site required by TinnR, you would notice the part of the code I send earlier: # check necesary packages necessary = c('TinnR', 'svSocket') installed = necessary %in% installed.packages()[, 'Package'] if (length(necessary[!installed]) =1) install.packages(necessary[!installed], dep=T). These are executed by the TinnR editor upon start. The TinnR package MUST therefore exist, and is required. Hope that someone else can REALLY help. Martin David Winsemius wrote: Tinn-R is not an R package. It is a standalone text editor: http://www.lmgtfy.com/?q=tinn-r -- David Winsemius On Mar 24, 2009, at 7:05 AM, Martin Tomko wrote: I have troubles make TinnR 2.2.0.2 work, it seems that the dependency on the package TinnR that cannot be found (I tried also manual downloads, but I cannot find the package anywhere on any CRAN mirror). I even set a default cran mirror in the Rprofile.site file, so that the later command can find it: # check necesary packages necessary = c('TinnR', 'svSocket') installed = necessary %in% installed.packages()[, 'Package'] if (length(necessary[!installed]) =1) install.packages(necessary[!installed], dep=T). No luck. Even manually issuing the comand in Rterm fails, package ‘TinnR’ is not available. Any idea how I could make my TinnR work? I googled extensively, but without luck... Thanks Martin __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code. David Winsemius, MD Heritage Laboratories West Hartford, CT __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
Re: [R] r online
Google with rweb -- David Winsemius On Mar 24, 2009, at 7:06 AM, Thomas Steiner wrote: Hi, I'd like to execute simple commands and functions in R through a website, is there any service like this somewhere? I only found http://www.osvisions.com/r-online/ but it does not work (last update 2003) and the links to releated websites only give errors (if I calculate 7+3). Thanks for help hints, Thomas __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code. David Winsemius, MD Heritage Laboratories West Hartford, CT __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
Re: [R] install.package(TinnR) - there is no package called 'TinnR'
Hi Martin, If all else fails, you could download the package from http://cran.r-project.org/web/packages/TinnR/index.html and install as a .zip file from within R. That is bizarre that R cannot find the package. I've had no problems downloading and installing. Best regards, Patrick -Original Message- From: r-help-boun...@r-project.org [mailto:r-help-boun...@r-project.org] On Behalf Of Martin Tomko Sent: Tuesday, March 24, 2009 8:25 AM To: David Winsemius Cc: r-help@r-project.org Subject: Re: [R] install.package(TinnR) - there is no package called 'TinnR' David, that is not helpful. I KNOW that TinnR is a standalone editor. If you had a look at the Rprofile.site required by TinnR, you would notice the part of the code I send earlier: # check necesary packages necessary = c('TinnR', 'svSocket') installed = necessary %in% installed.packages()[, 'Package'] if (length(necessary[!installed]) =1) install.packages(necessary[!installed], dep=T). These are executed by the TinnR editor upon start. The TinnR package MUST therefore exist, and is required. Hope that someone else can REALLY help. Martin David Winsemius wrote: Tinn-R is not an R package. It is a standalone text editor: http://www.lmgtfy.com/?q=tinn-r -- David Winsemius On Mar 24, 2009, at 7:05 AM, Martin Tomko wrote: I have troubles make TinnR 2.2.0.2 work, it seems that the dependency on the package TinnR that cannot be found (I tried also manual downloads, but I cannot find the package anywhere on any CRAN mirror). I even set a default cran mirror in the Rprofile.site file, so that the later command can find it: # check necesary packages necessary = c('TinnR', 'svSocket') installed = necessary %in% installed.packages()[, 'Package'] if (length(necessary[!installed]) =1) install.packages(necessary[!installed], dep=T). No luck. Even manually issuing the comand in Rterm fails, package 'TinnR' is not available. Any idea how I could make my TinnR work? I googled extensively, but without luck... Thanks Martin __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code. David Winsemius, MD Heritage Laboratories West Hartford, CT __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code. This email message, including any attachments, is for th...{{dropped:6}} __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
[R] CONFIDENCE INTERVAL FOR GLMER MODEL
I've built a poisson regression model for multiple subjects by using the GLMER function. I've also developed some curves for defining its limits but I did not succeed in developing confidence interval for the model's curve (confint or predict does not work - only for glm). Does anyone know how can I produce confidence interva for a glmer model? I'll appriciate any help... Liat -- View this message in context: http://www.nabble.com/CONFIDENCE-INTERVAL-FOR-GLMER-MODEL-tp22677543p22677543.html Sent from the R help mailing list archive at Nabble.com. __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
Re: [R] Variogram with Gstat
Have a look at the examples in the helpfile for variogram from the gstat package. data(meuse) # no trend: coordinates(meuse) = ~x+y variogram(log(zinc)~1, meuse) # residual variogram w.r.t. a linear trend: variogram(log(zinc)~x+y, meuse) # directional variogram: variogram(log(zinc)~x+y, meuse, alpha=c(0,45,90,135)) # GLS residual variogram: v = variogram(log(zinc)~x+y, meuse) v.fit = fit.variogram(v, vgm(1, Sph, 700, 1)) v.fit set = list(gls=1) v g = gstat(NULL, log-zinc, log(zinc)~x+y, meuse, model=v.fit, set = set) variogram(g) if (require(rgdal)) { proj4string(meuse) = CRS(+init=epsg:28992) meuse.ll = spTransform(meuse, CRS(+proj=longlat)) # variogram of unprojected data, using great-circle distances, returning km as units variogram(log(zinc) ~ 1, meuse.ll) } HTH, Thierry ir. Thierry Onkelinx Instituut voor natuur- en bosonderzoek / Research Institute for Nature and Forest Cel biometrie, methodologie en kwaliteitszorg / Section biometrics, methodology and quality assurance Gaverstraat 4 9500 Geraardsbergen Belgium tel. + 32 54/436 185 thierry.onkel...@inbo.be www.inbo.be To call in the statistician after the experiment is done may be no more than asking him to perform a post-mortem examination: he may be able to say what the experiment died of. ~ Sir Ronald Aylmer Fisher The plural of anecdote is not data. ~ Roger Brinner The combination of some data and an aching desire for an answer does not ensure that a reasonable answer can be extracted from a given body of data. ~ John Tukey -Oorspronkelijk bericht- Van: r-help-boun...@r-project.org [mailto:r-help-boun...@r-project.org] Namens giuseppef...@libero.it Verzonden: dinsdag 24 maart 2009 12:45 Aan: r-help@r-project.org Onderwerp: [R] Variogram with Gstat Dear all can you help me? i have this problem: i have a dataset in a text file in a matrix of 3 columns: x, y, z where x and y are the coordinates and Z are the mesurements. How can i do a variogram with R? __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code. Dit bericht en eventuele bijlagen geven enkel de visie van de schrijver weer en binden het INBO onder geen enkel beding, zolang dit bericht niet bevestigd is door een geldig ondertekend document. The views expressed in this message and any annex are purely those of the writer and may not be regarded as stating an official position of INBO, as long as the message is not confirmed by a duly signed document. __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
Re: [R] install.package(TinnR) - there is no package called 'TinnR'
Patrick, Romain, thank you very much for your help! I have found the site of the package at http://r-forge.r-project.org/projects/tinnr/ , as Romain suggests, but when you try to download, iyou find that the package is actually not contributed to the repository, it is just a space holder for it! Patrick's http://cran.r-project.org/web/packages/TinnR/index.html is better, and I will give it a try... I was just not sure abouyt the versions, but it seems to be a relatively recent one, so hopefully it will work. Thanks again! Martin Richardson, Patrick wrote: Hi Martin, If all else fails, you could download the package from http://cran.r-project.org/web/packages/TinnR/index.html and install as a .zip file from within R. That is bizarre that R cannot find the package. I've had no problems downloading and installing. Best regards, Patrick -Original Message- From: r-help-boun...@r-project.org [mailto:r-help-boun...@r-project.org] On Behalf Of Martin Tomko Sent: Tuesday, March 24, 2009 8:25 AM To: David Winsemius Cc: r-help@r-project.org Subject: Re: [R] install.package(TinnR) - there is no package called 'TinnR' David, that is not helpful. I KNOW that TinnR is a standalone editor. If you had a look at the Rprofile.site required by TinnR, you would notice the part of the code I send earlier: # check necesary packages necessary = c('TinnR', 'svSocket') installed = necessary %in% installed.packages()[, 'Package'] if (length(necessary[!installed]) =1) install.packages(necessary[!installed], dep=T). These are executed by the TinnR editor upon start. The TinnR package MUST therefore exist, and is required. Hope that someone else can REALLY help. Martin David Winsemius wrote: Tinn-R is not an R package. It is a standalone text editor: http://www.lmgtfy.com/?q=tinn-r -- David Winsemius On Mar 24, 2009, at 7:05 AM, Martin Tomko wrote: I have troubles make TinnR 2.2.0.2 work, it seems that the dependency on the package TinnR that cannot be found (I tried also manual downloads, but I cannot find the package anywhere on any CRAN mirror). I even set a default cran mirror in the Rprofile.site file, so that the later command can find it: # check necesary packages necessary = c('TinnR', 'svSocket') installed = necessary %in% installed.packages()[, 'Package'] if (length(necessary[!installed]) =1) install.packages(necessary[!installed], dep=T). No luck. Even manually issuing the comand in Rterm fails, package 'TinnR' is not available. Any idea how I could make my TinnR work? I googled extensively, but without luck... Thanks Martin __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code. David Winsemius, MD Heritage Laboratories West Hartford, CT __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code. This email message, including any attachments, is for ...{{dropped:5}} __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
Re: [R] install.package(TinnR) - there is no package called 'TinnR'
On 3/24/2009 7:05 AM, Martin Tomko wrote: I have troubles make TinnR 2.2.0.2 work, it seems that the dependency on the package TinnR that cannot be found (I tried also manual downloads, but I cannot find the package anywhere on any CRAN mirror). What R version are you using, on what platform? I have no trouble with an automatic install of the TinnR package into 2.8.1 on Windows. Duncan Murdoch I even set a default cran mirror in the Rprofile.site file, so that the later command can find it: # check necesary packages necessary = c('TinnR', 'svSocket') installed = necessary %in% installed.packages()[, 'Package'] if (length(necessary[!installed]) =1) install.packages(necessary[!installed], dep=T). No luck. Even manually issuing the comand in Rterm fails, package ‘TinnR’ is not available. Any idea how I could make my TinnR work? I googled extensively, but without luck... Thanks Martin __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code. __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
Re: [R] Calculating percentage Missing value for variables using one object
It looks to me that you should be using the table or the xtabs function. You have apparently already decided not to use NA for missing values, so the instances in which variable1 == you should get counts with those functions: dft - data.frame(var1 = sample(c(, this, that, and), 120, replace=TRUE), dt = sample( seq(as.Date(2006-01-01), as.Date(2007-12-31), by=months), 120, replace=TRUE)) mo.tbl - xtabs( ~var1+ dt, data=dft) # the == entry is the first row mo.tbl[1,] 2006-01-01 2006-02-01 2006-03-01 2006-04-01 2006-05-01 2006-06-01 2006-07-01 2 1 1 2 2 3 1 2006-08-01 2006-09-01 2006-10-01 2006-11-01 2006-12-01 2007-01-01 2007-02-01 0 1 1 1 2 1 2 2007-03-01 2007-04-01 2007-05-01 2007-06-01 2007-07-01 2007-08-01 2007-09-01 2 2 2 0 1 3 4 2007-10-01 2007-11-01 2007-12-01 1 3 2 x - seq(as.Date(2006-01-01), as.Date(2007-03-31), by=months) plot(mo.tbl[1,]~x) -- David Winsemius On Mar 24, 2009, at 2:58 AM, Shreyasee wrote: Hi, I have a dataset in which there are in all 250 variables and for each variable the data is entered over the months. I need to calculate the percentage of missing values for each variable over each month and then plot a graph for that. I am running the following code for doing the same *ds - read.csv(file=filepath, header=TRUE) attach(ds) may - length(variable1[variable1==]) / length(dos[dos==May-06]) * 100 jun - length(variable1[variable1==]) / length(dos[dos==June-06]) * 100 . . . var1 - c(may, jun, ...) x - seq(as.Date(2006-01-01), as.Date(2007-03-31), by=months) plot(var1~x)* So likewise I am calculating the percentage of missing values for each variable for each month using different variables and storing the values in those variables and then combining those variables in one object for plotting the graph. I need to know, whether can I combine all the variables from that dataset in one object and calculate the missing values percentage over months together, instead of creating different variables for each month and then combining them. Also, after doing that, I need to plot the graph for each variable and combine it in a single pdf file. I highly appreciate all your help. Thanks, Shreyasee [[alternative HTML version deleted]] __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code. David Winsemius, MD Heritage Laboratories West Hartford, CT __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
Re: [R] install.package(TinnR) - there is no package called 'TinnR' (RESOLVED)
Hi Duncan, it is Win Xp with the 2.6.0 R-project version. Sorry, I should have included this before. Installing the TinnR package manually from a local zip file downloaded from CRAN helped. I am still not sure why the package was not picked in the repositories. Can anyone please see if the package is visible to other under install packages in any repository? Thanks Martin Duncan Murdoch wrote: On 3/24/2009 7:05 AM, Martin Tomko wrote: I have troubles make TinnR 2.2.0.2 work, it seems that the dependency on the package TinnR that cannot be found (I tried also manual downloads, but I cannot find the package anywhere on any CRAN mirror). What R version are you using, on what platform? I have no trouble with an automatic install of the TinnR package into 2.8.1 on Windows. Duncan Murdoch I even set a default cran mirror in the Rprofile.site file, so that the later command can find it: # check necesary packages necessary = c('TinnR', 'svSocket') installed = necessary %in% installed.packages()[, 'Package'] if (length(necessary[!installed]) =1) install.packages(necessary[!installed], dep=T). No luck. Even manually issuing the comand in Rterm fails, package ‘TinnR’ is not available. Any idea how I could make my TinnR work? I googled extensively, but without luck... Thanks Martin __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code. __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
Re: [R] help: what are the basis functions in {mgcv}: gam?
Thank you very much. I have downloaded your paper. Best regards. Olivia Simon Wood-4 wrote: If you can't get hold of the book, try appendix A of http://www.maths.bath.ac.uk/~sw283/simon/papers/psm.pdf -- what's described there is the cr basis best, Simon On Tuesday 24 March 2009 05:01, oliviax wrote: Thanks for Andrew Robinson's suggestion. I am sorry that I have been looking for the book Wood (2006) Generalized Additive Models: Introduction with R for a long time in my univerity and book stores, but I failed to find one. I think it may take a long time to buy one from the Internet, and we are required to submit the master thesis soon... Could any one help me if you know other references or have knowledge about this?? I will be very very thankful. Sincerely yours, Olivia oliviax wrote: I am writing my thesis with the function gam(), with the package {mgcv}. My command is: gam(y~s(x1,bs=cr)+s(x2, bs=cr)). I need help to know what are the default basis funcitons for gam. I have not found any detailed reference for this. Can anyone help me with this?? -- Simon Wood, Mathematical Sciences, University of Bath, Bath, BA2 7AY UK +44 1225 386603 www.maths.bath.ac.uk/~sw283 __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code. -- View this message in context: http://www.nabble.com/help%3A-what-are-the-basis-functions-in-%7Bmgcv%7D%3A-gam--tp22673295p22679875.html Sent from the R help mailing list archive at Nabble.com. __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
[R] RES: Plot Means Line with Standard Deviation as Whiskers
Thanks for the answer, I'll take a look at these, meanwhile I forged some data as an example of what I'll have soon. Sam.Vol. A1R179,40 A1R2102,09 A1R3102,09 A2R1124,78 A2R2158,81 A2R3153,13 A3R1226,87 A3R2164,48 A3R3153,13 A4R1181,49 A4R2175,82 A4R3170,15 A5R1175,82 A5R2175,82 A5R3289,25 B1R1119,10 B1R2204,18 B1R3232,54 B2R1164,48 B2R2113,43 B2R3130,45 B3R1102,09 B3R2107,76 B3R3107,76 B4R1136,12 B4R2158,81 B4R3198,51 C1R176,30 C1R270,65 C1R362,17 C2R176,30 C2R270,65 C2R373,48 C3R150,87 C3R284,78 C3R3110,21 C4R1141,79 C4R2175,82 C4R3102,09 C5R190,43 C5R2113,04 C5R3141,30 D1R162,17 D1R242,39 D1R353,69 D2R167,82 D2R267,82 D2R359,35 D4R168,06 D5R1153,13 D5R2119,10 D5R3119,10 E1R1141,79 E1R285,07 E1R3107,76 E2R1130,45 E2R2175,82 E2R3107,76 E5R1158,81 F1R151,04 F1R290,75 F1R385,07 F2R173,73 F2R268,06 F2R373,73 F3R134,03 F3R239,70 F3R339,70 F4R139,70 F4R239,70 F4R351,04 G1R190,75 G1R262,39 G2R168,06 G2R279,40 G2R385,07 G3R1158,81 G3R2158,81 G3R3158,81 G5R145,37 G5R239,70 G5R351,04 H1R145,37 H1R2102,09 H1R345,37 H2R117,01 H2R222,69 H2R322,69 H3R168,06 H3R268,06 H3R345,37 H4R151,04 H4R245,37 H4R385,07 H5R156,72 H5R279,40 H5R373,73 I1R185,07 I1R273,73 I1R368,06 I2R1141,79 I2R2119,10 I2R3119,10 I3R173,73 I4R162,39 I4R245,37 I4R373,73 I5R1204,18 I5R2158,81 I5R3181,49 -Mensagem original- De: Peter Alspach [mailto:palsp...@hortresearch.co.nz] Enviada em: segunda-feira, 23 de março de 2009 19:55 Para: Rodrigo Aluizio; R Help Assunto: RE: [R] Plot Means Line with Standard Deviation as Whiskers Tena koe Rodrigo You could always make up some data and then show us what you have tried to do. I would guess you need to check out: plot # to do the basic plot lines # to add lines to the plot points # to add points to the plot arrows # can be used to give the whiskers apply # to get the means and standard deviations HTH Peter Alspach -Original Message- From: r-help-boun...@r-project.org [mailto:r-help-boun...@r-project.org] On Behalf Of Rodrigo Aluizio Sent: Tuesday, 24 March 2009 11:44 a.m. To: R Help Subject: [R] Plot Means Line with Standard Deviation as Whiskers Hi list members. I'll try to plot the abundance means of nine transects as lines, with five points on each transect (A to I). I will also need to plot for each point, it's standard deviation (once each point will have tree replicates) as whiskers. Another problem will be that all the points should exist for each transect, but we know that six of the nine transects will have blanks (A1, A2, A3, -, A5). So the line have to be interrupted and can't induce an inexistent value by link A3 to A5 (an example). Well, unfortunately I still don't have the data, I'm just anticipating a future situation, and I can't find any clear suggestion by googling the issue, and I guess the help files may have something but I was unable to find by myself. Thanks in advance. Any help will be appreciated. - MSc. mailto:r.alui...@gmail.com Rodrigo Aluizio Centro de Estudos do Mar/UFPR Laboratório de Micropaleontologia Avenida Beira Mar s/n - CEP 83255-000 Pontal do Paraná - PR - Brasil Fone: (0**41) 3455-3620 ramal 217 Fax: (0**41) 3455-3623 [[alternative HTML version deleted]] The contents of this e-mail are confidential and may be ...{{dropped:15}} __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
Re: [R] install.package(TinnR) - there is no package called 'TinnR' (RESOLVED)
Martin Tomko wrote: Hi Duncan, it is Win Xp with the 2.6.0 R-project version. Sorry, I should have included this before. Installing the TinnR package manually from a local zip file downloaded from CRAN helped. I am still not sure why the package was not picked in the repositories. Can anyone please see if the package is visible to other under install packages in any repository? Please upgrade to a recent version of R! We do not build binary packages for completely out of date versions of R. Uwe Ligges Thanks Martin Duncan Murdoch wrote: On 3/24/2009 7:05 AM, Martin Tomko wrote: I have troubles make TinnR 2.2.0.2 work, it seems that the dependency on the package TinnR that cannot be found (I tried also manual downloads, but I cannot find the package anywhere on any CRAN mirror). What R version are you using, on what platform? I have no trouble with an automatic install of the TinnR package into 2.8.1 on Windows. Duncan Murdoch I even set a default cran mirror in the Rprofile.site file, so that the later command can find it: # check necesary packages necessary = c('TinnR', 'svSocket') installed = necessary %in% installed.packages()[, 'Package'] if (length(necessary[!installed]) =1) install.packages(necessary[!installed], dep=T). No luck. Even manually issuing the comand in Rterm fails, package ‘TinnR’ is not available. Any idea how I could make my TinnR work? I googled extensively, but without luck... Thanks Martin __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code. __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code. __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
Re: [R] CONFIDENCE INTERVAL FOR GLMER MODEL
On Tue, Mar 24, 2009 at 5:25 AM, LiatL liat.lam...@gmail.com wrote: I've built a poisson regression model for multiple subjects by using the GLMER function. I've also developed some curves for defining its limits but I did not succeed in developing confidence interval for the model's curve (confint or predict does not work - only for glm). Does anyone know how can I produce confidence interva for a glmer model? I'll appriciate any help... You would need to be more explicit about what you mean by the model's curve and what the confidence interval would represent, in the sense of what components of the variability would be incorporated in the confidence interval, before we could answer such a question. May I suggest that the discussion be moved to the r-sig-mixed-mod...@r-project.org mailing list, which I have cc:d on this reply? __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
Re: [R] Calculating percentage Missing value for variables using one object
Read in the data, aggregate it by month and then turn it into a monthly zoo object and plot using a custom X axis: Lines - 'dos,variable1,variable2 May-06,1, May-06,2, June-06,,2 June-06,1,4 July-06,1,4 July-06,1,4 August-06,1,4 August-06,1,4' DF - read.table(textConnection(Lines), header = TRUE, sep = ,) library(zoo) DF.na - aggregate(DF[-1], DF[dos], function(x) mean(is.na(x))) z - zoo(as.matrix(DF.na[-1]), as.yearmon(DF.na$dos, %B-%y)) i - 1 plot(z[,i], xaxt = n, ylab = Fraction Missing, main = names(DF)[i+1]) axis(1, time(z), format(time(z), %m/%y), cex.axis = .7) On Tue, Mar 24, 2009 at 2:58 AM, Shreyasee shreyasee.prad...@gmail.com wrote: Hi, I have a dataset in which there are in all 250 variables and for each variable the data is entered over the months. I need to calculate the percentage of missing values for each variable over each month and then plot a graph for that. I am running the following code for doing the same *ds - read.csv(file=filepath, header=TRUE) attach(ds) may - length(variable1[variable1==]) / length(dos[dos==May-06]) * 100 jun - length(variable1[variable1==]) / length(dos[dos==June-06]) * 100 . . . var1 - c(may, jun, ...) x - seq(as.Date(2006-01-01), as.Date(2007-03-31), by=months) plot(var1~x)* So likewise I am calculating the percentage of missing values for each variable for each month using different variables and storing the values in those variables and then combining those variables in one object for plotting the graph. I need to know, whether can I combine all the variables from that dataset in one object and calculate the missing values percentage over months together, instead of creating different variables for each month and then combining them. Also, after doing that, I need to plot the graph for each variable and combine it in a single pdf file. I highly appreciate all your help. Thanks, Shreyasee [[alternative HTML version deleted]] __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code. __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
Re: [R] install.package(TinnR) - there is no package called 'TinnR' (RESOLVED)
On 3/24/2009 8:55 AM, Martin Tomko wrote: Hi Duncan, it is Win Xp with the 2.6.0 R-project version. Sorry, I should have included this before. Installing the TinnR package manually from a local zip file downloaded from CRAN helped. I am still not sure why the package was not picked in the repositories. Can anyone please see if the package is visible to other under install packages in any repository? Your version of R is too old. TinnR was last updated in February this year and claims to support 2.6.0, but CRAN no longer builds binaries for 2.6.x. (Version 2.6.0 became obsolete in November 2007 when 2.6.1 was released, and binaries for the 2.6.x series stopped being built sometime last year.) If you are set up for installing from source, you could try downloading the source package http://cran.r-project.org/src/contrib/TinnR_1.0.3.tar.gz and running Rcmd INSTALL TinnR_1.0.3.tar.gz but it is probably easier to update your R to the current release. Duncan Murdoch Thanks Martin Duncan Murdoch wrote: On 3/24/2009 7:05 AM, Martin Tomko wrote: I have troubles make TinnR 2.2.0.2 work, it seems that the dependency on the package TinnR that cannot be found (I tried also manual downloads, but I cannot find the package anywhere on any CRAN mirror). What R version are you using, on what platform? I have no trouble with an automatic install of the TinnR package into 2.8.1 on Windows. Duncan Murdoch I even set a default cran mirror in the Rprofile.site file, so that the later command can find it: # check necesary packages necessary = c('TinnR', 'svSocket') installed = necessary %in% installed.packages()[, 'Package'] if (length(necessary[!installed]) =1) install.packages(necessary[!installed], dep=T). No luck. Even manually issuing the comand in Rterm fails, package ‘TinnR’ is not available. Any idea how I could make my TinnR work? I googled extensively, but without luck... Thanks Martin __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code. __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code. __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
Re: [R] install.package(TinnR) - there is no package called 'TinnR' (RESOLVED)
Yes, will do. I just was not in need to upgrade as everything worked... An R is not my primary development environment - i.e., I need it a couple of times a year. But you are right, it is good to be on an updated version. Cheers Martin Duncan Murdoch wrote: On 3/24/2009 8:55 AM, Martin Tomko wrote: Hi Duncan, it is Win Xp with the 2.6.0 R-project version. Sorry, I should have included this before. Installing the TinnR package manually from a local zip file downloaded from CRAN helped. I am still not sure why the package was not picked in the repositories. Can anyone please see if the package is visible to other under install packages in any repository? Your version of R is too old. TinnR was last updated in February this year and claims to support 2.6.0, but CRAN no longer builds binaries for 2.6.x. (Version 2.6.0 became obsolete in November 2007 when 2.6.1 was released, and binaries for the 2.6.x series stopped being built sometime last year.) If you are set up for installing from source, you could try downloading the source package http://cran.r-project.org/src/contrib/TinnR_1.0.3.tar.gz and running Rcmd INSTALL TinnR_1.0.3.tar.gz but it is probably easier to update your R to the current release. Duncan Murdoch Thanks Martin Duncan Murdoch wrote: On 3/24/2009 7:05 AM, Martin Tomko wrote: I have troubles make TinnR 2.2.0.2 work, it seems that the dependency on the package TinnR that cannot be found (I tried also manual downloads, but I cannot find the package anywhere on any CRAN mirror). What R version are you using, on what platform? I have no trouble with an automatic install of the TinnR package into 2.8.1 on Windows. Duncan Murdoch I even set a default cran mirror in the Rprofile.site file, so that the later command can find it: # check necesary packages necessary = c('TinnR', 'svSocket') installed = necessary %in% installed.packages()[, 'Package'] if (length(necessary[!installed]) =1) install.packages(necessary[!installed], dep=T). No luck. Even manually issuing the comand in Rterm fails, package ‘TinnR’ is not available. Any idea how I could make my TinnR work? I googled extensively, but without luck... Thanks Martin __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code. __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code. __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
Re: [R] Barplot With Selected X-Axis Region
Gundala Viswanath wrote: Dear all, I have a data that looks like this: print(dat) V1 V2 1 -43342073 14 2 -433377304 3 -432846761 11372 75188572 11 11373 752061656 11374 75262720 24 What I want to do is to have a barplot where x-axis is taken from V1 and y-axis taken from V2. But I only want to plot the those region where V1 = -500 and = 500. But some how this snippet doesn't seem to work: xlim = c(-500,500) barplot(as.matrix(dat[dat$V1 = -500 dat$V1 =500,dat$V2]),xlim=xlim,axes=TRUE, main =nm); You need to change dat$V1 = -500 dat$V1 =500 to dat$V1 = -500 dat$V1 =500 and read about the difference between and . So probably you want something like: subsetdat - dat[dat$V1 = -500 dat$V1 =500,] barplot(subsetdat$V2, names.arg=subsetdat$V1) Uwe Ligges What's wrong with my approach. So yes, I do want the V1 information, hence I am aware that I dont' want: plot(hist(dat[dat =-500 dat =500])) - Gundala Viswanath Jakarta - Indonesia __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code. __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
[R] Do we have to control for block in block designs if it is insignificant?
I am wondering if in a block experimental design (ex. triple square lattice), the block effect was not significant, is it all right not to include the block effect in an empirical model (even though the sampling was done from different blocks)? Or we are forced to control for the block effect in block designs anyway? Thanks, Julia _ Internet Explorer 8 Now Available. Faster, safer, easier. [[alternative HTML version deleted]] __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
Re: [R] How to find the path or the current file?
Thank you Gabor and Duncan for your replys. Mvh. Marie On Tue, Mar 24, 2009 at 1:00 PM, Gabor Grothendieck ggrothendi...@gmail.com wrote: See: https://stat.ethz.ch/pipermail/r-help/2009-January/184745.html On Tue, Mar 24, 2009 at 7:16 AM, Marie Sivertsen mariesiv...@gmail.com wrote: Dear useRs, I have a collection of source file and some of these call others. The files are distribute among a number of directories, and to know how to call some other file they need to know what file is currently executed. As example, I have a file 'search.R' located in directory 'bin' which needs to access the file 'terms.conf' located in the directory 'conf', a sibling of 'bin'. I can have somethings like readLines('../conf/terms.conf') in search.R, but this work only if search.R is executed from bin, when getwd is 'bin'. But when search.R calls from the parent as bin/search.R or any other derectory then R complains that it could not find the file '../conf/terms.conf'. So my questions is: how can the file search.R, when executied, discover its own location and load terms.conf from location of search.R/../conf/terms.conf? the location of search.R can be unrelated to the current directory. Mvh. Marie [[alternative HTML version deleted]] __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code. [[alternative HTML version deleted]] __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
[R] as.list cannot handle an environment
?as.list states that as.list can be used with environments as arguments (what is referred to there as the 'environment method for as.list). indeed, e = globalenv() as.list(e) # $e # environment: R_GlobalEnv however, it seems to have problems with environment objects with a class attribute: e = structure(globalenv(), class='foo') as.list(e) # Error in as.vector(x, list) : # cannot coerce type 'environment' to vector of type 'list' the error message is misleading. instead of complaining about the class 'foo', it says that as.list cannot coerce an environment to a list, which is nonsense, since this is precisely what it does in the first example above, and what is also clear from ?as.list: The 'environment' method for 'as.list' copies the name-value pairs (for names not beginning with a dot) from an environment to a named list. a different error message might be more appropriate. vQ __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
[R] Help with lattice
Hello. I'm working on a windows XP machine with R 2.8.1 I'm working with lattice and I don't understand how to set the size of the text for the labels. Can anyone suggest a solution? I'm establishing a melted dataframe first and then setting a key and calling the plot as follows; key.variable - list(space = right, text = list(levels(wbirdm$variable)), points = list(pch = 1:3, col=c(1:9))) dotplot(wbirdm$value ~ wbirdm$variable | wbirdm$Region, col=c(1:9), pch= rep(c(1:3), key = key.variable, groups=wbirdm$variable, ylab= Mean HSI)) This works pretty well, with the exception that the size of x axis labels is too large. Also, the key does not appear. I do appreciate all of the help this group provides. Thanks Steve Friedman Ph. D. Spatial Statistical Analyst Everglades and Dry Tortugas National Park 950 N Krome Ave (3rd Floor) Homestead, Florida 33034 steve_fried...@nps.gov Office (305) 224 - 4282 Fax (305) 224 - 4147 __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
[R] using residuals of binomial GLM
Hi all, This is more a question in statistics, but I hope to get also the R practice for my question: I have an ancova model where the response variable is flowering (plant has a flower = 1, no flower = 0). The explanatory variables are leaf length, leaf thick (both continuous variables), and soil type (factorial with three levels): model-glm(flower~(thick+length)*soil,family=binomial) summary(aov(model)) In the aov summary I find a significant effect of all variables, and a significant interaction between thick and soil, so I want to explore this interaction after cleaning the effect of length. I thought of two possible ways to extract the residuals: res.thick-resid(update(model,~.-thick-soil-thick:soil)) or: res.thick-resid(glm(flower~length+length:soil,family=binomial)) I validated that the two methods give the same results. Anyhow, now I want to compare the effect of thick on flowering probability,separately for each soil. But the residuals extracted are not 0 or 1 anymore. Linear glm, such as model1-glm(res.thick1~thick*soil) doesn't seem to be right, and, moreover, I am interested in the estimated coefficients and their interpretation (say - plotting a meaningful graph). How can I get a logistic regression from residuals? Do I NEED logistic regression? How should I understand the coefficients I get in summary of the residuals model? How can I use the results of the residuals model for plotting the separate lines for the probability (logistic) curve? Thanks in advance Yuval -- Yuval Sapir, PhD Porter School of Environmental Studies Dept. of Plant Sciences Tel Aviv University, Tel Aviv, 69978 Israel Mobile:054-7203140; Lab: 03-6405877 http://www.yeruka.org.il/ __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
Re: [R] Random sampling based on the observations
Thank you Adrian. Its working.Thank you so much. Take care =^D=) Cheers Arup Pramanik Business Analyst Redwood Associates Bangalore,India. Adrian Dusa wrote: On Tuesday 24 March 2009, you wrote: Hello!I am having a problem with Random sampling in R. I have used a syntax: mydata.sub=sample(mydata,7,replace=FALSE,prob=NULL) which allows me to choose a random sample based on the variables(correct me if I am wrong!). Actually, no. You are sampling from a vector, and where you're using the sampled values (on the rows or on the variables) is up to you. Let's say we have a dataset with 100 cases and 10 variables: Case 1: mydata.sub - mydata[ , sample(10, 7)] This will sample 7 variables out of 10. Case 2: mydata.sub - mydata[sample(100, 10), ] This will sample 10 cases out of 100. Suppose I have 10 variable and if I use the above mentioned command then it will choose 7 variables out of the 10 randomly. My problem is that I want to have a random sample which is not based on the variables but on the values of the variables that is the random sample will be based on the observations. It will be great if someone can help me out me out with a proper syntax. Thanks in Advance. I think you need to read the help for: ?[ and most probably one of the introductory books for R. I hope this helps, Adrian -- Adrian Dusa Romanian Social Data Archive 1, Schitu Magureanu Bd. 050025 Bucharest sector 5 Romania Tel.:+40 21 3126618 \ +40 21 3120210 / int.101 Fax: +40 21 3158391 [[alternative HTML version deleted]] __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code. -- View this message in context: http://www.nabble.com/Random-sampling-based-on-the-observations-tp22673975p22681075.html Sent from the R help mailing list archive at Nabble.com. __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
[R] Has someone connected R with ITK?
Dear R users, I am curious to know if someone has connected R with the Insight Segmentation and Registration Toolkit (www.itk.org). From the website... ITK is an open-source, cross-platform system that provides developers with an extensive suite of software tools for image analysis. Developed through extreme programming methodologies, ITK employs leading-edge algorithms for registering and segmenting multidimensional data. A project already exists to provide a matlab-based interface to ITK at Simon Fraser University (matitk.cs.sfu.ca), but I would prefer a 100% open-source platform. Searching through the R-site and R-help produced zero hits, so I assume it has not been attempted or at least not announced anywhere. If anyone would be interested in participating in such an endeavour, please feel free to contact me. cheers... Brandon --- This e-mail was sent by GlaxoSmithKline Services Unlimited (registered in England and Wales No. 1047315), which is a member of the GlaxoSmithKline group of companies. The registered address of GlaxoSmithKline Services Unlimited is 980 Great West Road, Brentford, Middlesex TW8 9GS. --- [[alternative HTML version deleted]] __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
[R] Odp: error statement: missing value where TRUE/FALSE needed
Hi r-help-boun...@r-project.org napsal dne 23.03.2009 15:38:49: Hi list, I want to try Gibbs sampling as a method of estimating a markov-switching model of a mean-deviating, pth-order autoregressive process with time varying transition probabilities via R and am using a code originally written by another person; I attach the useful pdf document explaining the code. When I run the code, I get an error message: Error in if (r vQ[i]) { : missing value where TRUE/FALSE needed I am using R.2.6.0 on Windows XP. Can anyone tell me what the error message means? The error message means that there is missing value instead of logical when you are calling if a-NA b-1 ab [1] NA if(ab) print(No.way) Error in if (a b) print(No.way) : missing value where TRUE/FALSE needed a-0 if(ab) print(No.way) [1] No.way So test r and vQ if they contain missing values or change your code Besides, it looks like code written in Basic not in R Few other comments * read.table() already produce data frame * This is really strange, I did not see such construction yet mG0 -rbind(cbind(100,0,0,0), cbind(0,100,0,0), cbind(0,0,100,0), cbind(0,0,0,100)) what about x-matrix(0, 4,4) diag(x)-100 x [,1] [,2] [,3] [,4] [1,] 100000 [2,]0 10000 [3,]00 1000 [4,]000 100 * Better upgrade to 2.8.1, or maybe wait about a month for 2.9.0 * I do not think that somebody will go through whole your code, it is terribly complicated. Regards Petr The specific line in the code is: if (rvQ[i]){ vS[i]=0 } else vS[i]=1 The code is available at: http://www.michael-curran.com/gibbs.html and the two data sets are available at: http://www.geocities.jp/atsmatsumoto/ci.txt and http://www.geocities.jp/atsmatsumoto/callrate.txt Note: I saved the first data set as ci.txt and the second as boj.txt and so these are the file names that the code loads. If anyone uses the code and the data and manages to get it to work, I would gratefully appreciate if they could tell me what adjustments they made to the code in order to do so. Kind regards, Michael -- Michael Curran Candidate for the MPhil in Economics Cambridge University http://www.michael-curran.com/ [příloha gibbsms-1.pdf odstraněna uživatelem Petr PIKAL/CTCAP] __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code. __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
Re: [R] Do we have to control for block in block designs if it is insignificant?
The short answer is no (meaning to leave the blocks in the model). As Frank Harrell said, you've spent your degrees of freedom. Go home and be happy. Best, Andy From: J S Sent: Tuesday, March 24, 2009 9:49 AM To: r-help@r-project.org Subject: [R] Do we have to control for block in block designs if it is insignificant? I am wondering if in a block experimental design (ex. triple square lattice), the block effect was not significant, is it all right not to include the block effect in an empirical model (even though the sampling was done from different blocks)? Or we are forced to control for the block effect in block designs anyway? Thanks, Julia _ Internet Explorer 8 - Now Available. Faster, safer, easier. [[alternative HTML version deleted]] Notice: This e-mail message, together with any attachme...{{dropped:12}} __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
[R] how to do trend.test for subset data
Dear: I try to do the trend.test {pastecs} for a subset data. Anyone have this experience? Many thanks! Xin __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
[R] Hotteling Test
Hi listers, I would like to do a graphic of the power function of the Hotteling test (T2). T2~F(p,n-p;lambda), lambda is my paremeter of non-centrality. So I would like to do a graphic of the power of the test as a function of the parameter lambda. I also would like to define lambda varying between 0.05 and 1. I am really not sure if the way that I am doing the graphic is the best methodology. I am working on this code... N-20 p-3 alpha-0.05 mean0-matrix(c(0,0,0),nrow=3,ncol=1,byrow=TRUE) mean1-matrix(c(0,1,0),nrow=3,ncol=1,byrow=TRUE) sigma-matrix(c(1,0.2,-0.8,0.2,1,0.4,-0.8,0.4,1),nrow=3,ncol=3,byrow=TRUE) T2-N*(t((mean1-mean0))%*%solve(sigma)%*%(mean1-mean0)) lambda-N*(t((mean1-mean0))%*%solve(sigma)%*%(mean1-mean0))/2 critique-qf(1-alpha,3,17)#critique ~ Fp,n-p(α) beta-1-pf(critique,p,n-p,ncp=lambda) beta beta1-c(rep(0,112)) lambda1-c(1:112) for (i in 1:112){ beta1[i]-1-pf(critique,p,N-p,ncp=lambda1[i]) } if (0.05beta11){ plot(beta1,pch=.) } Thanks, Marcio -- View this message in context: http://www.nabble.com/Hotteling-Test-tp22682412p22682412.html Sent from the R help mailing list archive at Nabble.com. __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
Re: [R] How to find the path or the current file?
I sometimes deal with this problem by putting all the scripts into a package (in the inst/ directory if they don't fit elsewhere, perhaps in demo/) and then have them all use system.file(package=myPkg,...) to locate the related files. E.g., terms.conf - system.file(package=myPkg,conf,terms.conf) if (terms.conf==) stop(Cannot find , file.path(conf,terms.conf), in package , myPkg) source(terms.conf) (It would be nice if system.file itself had an option to halt if no file could be found but one can write a wrapper for that.) Putting all the scripts in a package also makes them easier to deploy on other machines. By using the Depends: line in the DESCRIPTION file you can arrange for packages to have a core set of scripts available in a standard place. Bill Dunlap TIBCO Software Inc - Spotfire Division wdunlap tibco.com [R] How to find the path or the current file? Marie Sivertsen mariesivert at gmail.com Tue Mar 24 12:16:22 CET 2009 Dear useRs, I have a collection of source file and some of these call others. The files are distribute among a number of directories, and to know how to call some other file they need to know what file is currently executed. As example, I have a file 'search.R' located in directory 'bin' which needs to access the file 'terms.conf' located in the directory 'conf', a sibling of 'bin'. I can have somethings like readLines('../conf/terms.conf') in search.R, but this work only if search.R is executed from bin, when getwd is 'bin'. But when search.R calls from the parent as bin/search.R or any other derectory then R complains that it could not find the file '../conf/terms.conf'. So my questions is: how can the file search.R, when executied, discover its own location and load terms.conf from location of search.R/../conf/terms.conf? the location of search.R can be unrelated to the current directory. Mvh. Marie __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
Re: [R] how to do trend.test for subset data
That question seems too vague to be answered. There should be no problem in doing such. Do you have a problem that you are encountering? -- David Winsemius On Mar 24, 2009, at 10:52 AM, Xin Shi wrote: Dear: I try to do the trend.test {pastecs} for a subset data. Anyone have this experience? Many thanks! Xin __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code. David Winsemius, MD Heritage Laboratories West Hartford, CT __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
Re: [R] confidence interval or error of x intercept of a linear
(Ted Harding) wrote: On 24-Mar-09 03:31:32, Kevin J Emerson wrote: ... When I have time for it (not today) I'll see if I can implement this neatly in R. It's basically a question of solving (N-2)*(1 - R(X0))/R(X0) = qf(P,1,(N-1)) for X0 (two solutions, maybe one, if any exist). etc. A quick and probably not-too-dirty way is to rewrite it as a nonlinear model: x - 1:10 Y - 2*x - 3 + rnorm(10, sd=.1) cf - coef(lm(Y~x)) confint(nls(Y~beta*(x-x0), start=c(beta=cf[[2]],x0=-cf[[1]]/cf[[2]]))) -- O__ Peter Dalgaard Øster Farimagsgade 5, Entr.B c/ /'_ --- Dept. of Biostatistics PO Box 2099, 1014 Cph. K (*) \(*) -- University of Copenhagen Denmark Ph: (+45) 35327918 ~~ - (p.dalga...@biostat.ku.dk) FAX: (+45) 35327907 __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
Re: [R] R: how to estimate multidimensional spectral measure of coherence
Look at the function wco to see if you can use it. I don't have R on my work computer right now to test and see, but AI think you could look at this. I don't know what a slidding window is, but wavelets are time localized so I don't think this would be a problem. Also, you could easily slide the time series with lag. I don't know if this helps. stephen sefick On Mon, Mar 23, 2009 at 11:22 AM, mau...@alice.it wrote: Does it work on a sliding window ? Does it estimate the cospectrum (the real part) and the quadrature spectrum (complex), the coherence squared, and the phase difference between two vector time series ? SOme time ago I started to read its author's thesis. It seemed to me strictly tailored on the specific problems he studied more than a wider purpose toolkit. Maura have you tried sowas? I know you had talked about it, but it may do what you want. I have used it for the wavelet cross spectrum. On Mon, Mar 23, 2009 at 9:47 AM, mau...@alice.it wrote: Please, does anyone know of an R packge to estimate multidimensional spectral measure of coherence within a moving time window ? Some time ago I expeimented with a similar package that performs Cross Spectrum Analysis on the whole signal though. Unluckily I deal with non-stationary signals whose properties change along with time. Therefore estimates can only be made over time periods roughly proportional to the reciprocal of the rate at which properties are changing. Thank you very much. Maura tutti i telefonini TIM! [[alternative HTML version deleted]] __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code. -- Stephen Sefick Let's not spend our time and resources thinking about things that are so little or so large that all they really do for us is puff us up and make us feel like gods. We are mammals, and have not exhausted the annoying little problems of being mammals. -K. Mullis Alice Messenger ;-) chatti anche con gli amici di Windows Live Messenger e tutti i telefonini TIM! Vai su http://maileservizi.alice.it/alice_messenger/index.html?pmk=footer -- Stephen Sefick Let's not spend our time and resources thinking about things that are so little or so large that all they really do for us is puff us up and make us feel like gods. We are mammals, and have not exhausted the annoying little problems of being mammals. -K. Mullis __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
Re: [R] r online
Dirk Eddelbuettel edd at debian.org writes: On 24 March 2009 at 12:06, Thomas Steiner wrote: | Hi, | I'd like to execute simple commands and functions in R through a | website, is there any service like this somewhere? | I only found http://www.osvisions.com/r-online/ but it does not work | (last update 2003) and the links to releated websites only give errors | (if I calculate 7+3). | Thanks for help hints, Please read the R FAQ which has an entire section devoted to this that I include below, copied and pasted from the txt version of the R FAQ. Personally, I'd go with Rpad. To add to the FAQ that Dirk quotes: The Sage project has an online notebook server at sagenb.org that allows one to use numerous open source math programs including R. Sage can be installed locally as well. (The R feature seems to be broken at the moment though, but it does work on a local install.) The gWidgetsWWW package (needs testing still) provides an interface to Rpad that you could use to quickly create a web page to interpret R commands, e.g. the simplistic http://www.math.csi.cuny.edu/gWidgetsWWW/ex-cli.html. However, graphics are easier done using Rpad, than gWidgetsWWW. __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
[R] Display Equation on plot
Hello, I am using the lm to fit a linear model to data, I was wondering if there is a way to display the equation on a plot using the extracted lm coefficients? I am using the plot() function to create the plot/.png. Example: lm_mod - lm(data1~data2) intercept = 48.54 slope = 0.4856 I want to display equation on a plot as y=0.4856x+48.54 Any thoughts or suggestions are appreciated. Thanks, Doug -- - Douglas M. Hultstrand, MS Senior Hydrometeorologist Metstat, Inc. Windsor, Colorado voice: 970.686.1253 email: dmhul...@metstat.com web: http://www.metstat.com __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
Re: [R] Display Equation on plot
Douglas M. Hultstrand wrote: Hello, I am using the lm to fit a linear model to data, I was wondering if there is a way to display the equation on a plot using the extracted lm coefficients? I am using the plot() function to create the plot/.png. Example: lm_mod - lm(data1~data2) intercept = 48.54 slope = 0.4856 I want to display equation on a plot as y=0.4856x+48.54 Any thoughts or suggestions are appreciated. See ?abline: abline(lm_mod) Uwe Ligges Thanks, Doug __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
[R] no snowfall on debian after lenny upgrade
I feel like I've tried the works on something that should be obvious but I'm stuck. Package snowfall used to run just great under debian etch (amd-64, 2x quad-core). After upgrading to lenny (debian 5, reinstalled from scratch), I haven't been able to get snowfall running again. Password-less ssh works fine to localhost, its IP, or zero- config name. But when calling sfInit I invariably get this error message below. What puzzles me is that ssh localhost works without a hitch but the socket connection fails. Any suggestions would be greatly appreciated. Best, Martin Error in socketConnection(port = port, server = TRUE, blocking = TRUE, : cannot open the connection In addition: Warning message: In socketConnection(port = port, server = TRUE, blocking = TRUE, : port 10187 cannot be opened Error in sfInit() : Starting of snow cluster failed! Error in socketConnection(port = port, server = TRUE, blocking = TRUE, : cannot open the connection Error in socketConnection(port = port, server = TRUE, blocking = TRUE, : cannot open the connection Calls: source - eval.with.vis - eval.with.vis - sfInit Execution halted I've tried this with the stable debian version of R (2.7.1) as well as compiled from R-2.8.1 (with current snowfall) and the latest from sid (see below). platform x86_64-pc-linux-gnu arch x86_64 os linux-gnu system x86_64, linux-gnu status alpha major 2 minor 9.0 year 2009 month 03 day20 svn rev48169 language R version.string R version 2.9.0 alpha (2009-03-20 r48169) Martin Renner Postdoctoral Fellow School of Aquatic and Fishery Sciences University of Washington Seattle, WA 98195-5020, USA current address: Alaska Maritime NWR Homer, AK 99603, USA __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
Re: [R] Display Equation on plot
On 3/24/2009 12:50 PM, Douglas M. Hultstrand wrote: Hello, I am using the lm to fit a linear model to data, I was wondering if there is a way to display the equation on a plot using the extracted lm coefficients? I am using the plot() function to create the plot/.png. Example: lm_mod - lm(data1~data2) intercept = 48.54 slope = 0.4856 I want to display equation on a plot as y=0.4856x+48.54 mtext(bquote( y == .(slope) * x + .(intercept)), side=1, line=4) will put it in the bottom margin. Use text() with appropriate coordinates to put it in the plot area instead. Duncan Murdoch Any thoughts or suggestions are appreciated. Thanks, Doug __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
Re: [R] Display Equation on plot
Douglas M. Hultstrand dmhultst at metstat.com writes: Hello, I am using the lm to fit a linear model to data, I was wondering if there is a way to display the equation on a plot using the extracted lm coefficients? I am using the plot() function to create the plot/.png. Example: lm_mod - lm(data1~data2) intercept = 48.54 slope = 0.4856 I want to display equation on a plot as y=0.4856x+48.54 see ?bquote for building the equation expression and ?mtext to display text within margins e.g. # generate random x and y values x - rnorm(100) y - 3*x+15 + rnorm(x) lm_mod - lm(y ~ x) plot(x, y) abline(lm_mod) # add regression line to the plot lm_coef - round(coef(lm_mod), 3) # extract coefficients mtext(bquote(y == .(lm_coef[2])*x + .(lm_coef[1])), adj=1, padj=0) # display equation regards, Matthieu __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
[R] Testing for symbolic links
Hello, How can I test in R whether a file is a symbolic link or not ? I haven't found anything relevant in R-help but I may be wrong. Thanks ! Greg --- Gregoire Pau Research Officer EMBL Heidelberg, Germany http://www.ebi.ac.uk/~gpau/ __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
[R] generalized Poisson regression
Dear sir, I want to know about R command for parameter estimation for generalized Poisson regression. yours faithfully Arafat Ud Zaman 4th year(Hons) Applied statistics University of Dhaka Mob- +8801715173176 E-mail: arafat.za...@yahoo.com azam...@isrt.ac.bd azam...@quantummethod.org.bd [[alternative HTML version deleted]] __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
[R] Workspace Image
Hello, I'm wondering how to delete previously saved workspace in R. Thank you. Regards, Yikan Liu [[alternative HTML version deleted]] __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
[R] Why na.rm=FALSE is the default
Dear Colleagues, I've been searching for a post or article or something which explains why having na.rm=FALSE or na.action=na.fail as the default is a better choice than TRUE or na.omit. I understand the basic argument: it does not make sense to average a nonexistance into an aggregate, and removing them implicitly leads to accidental pairwise deletion in some cases, and sum(x) / length(x) mean(x) (which many would find disturbing)...I'm just looking for a source to cite on this issue to support mimicking R's behavior in a database system's aggregating functions (sum, avg, var, etc.). Cordially, Adam Kramer Ph.D. Candidate, Social Psychology University of Oregon adik at uoregon dot edu __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
Re: [R] generalized Poisson regression
Not 100% sure what you are looking for, but have a look at the Generalized Event Count model in the Zelig package. It will also let you fit a Poisson and other event count models by MLE. -Original Message- From: azam...@isrt.ac.bd Sent: Tue, 24 Mar 2009 23:26:59 +0600 To: r-help@r-project.org Subject: [R] generalized Poisson regression Dear sir, I want to know about R command for parameter estimation for generalized Poisson regression. yours faithfully Arafat Ud Zaman 4th year(Hons) Applied statistics University of Dhaka Mob- +8801715173176 E-mail: arafat.za...@yahoo.com azam...@isrt.ac.bd azam...@quantummethod.org.bd [[alternative HTML version deleted]] __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code. FREE 3D EARTH SCREENSAVER - Watch the Earth right on your desktop! Check it out at http://www.inbox.com/earth __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
[R] Search Errors
Hi R users, I have a big program So in Rgui I can t see all the execution of it Is there a way to ask R if there is Errors in my program Sincerely yours -- View this message in context: http://www.nabble.com/Search-%22Errors%22-tp22687080p22687080.html Sent from the R help mailing list archive at Nabble.com. __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
Re: [R] Workspace Image
Yikan Liu u4297812 at anu.edu.au writes: I'm wondering how to delete previously saved workspace in R. file.remove(mywork.rdata) Dieter __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
Re: [R] Summarizing each row into a frequency table
Have you tried table(row(m), m) ? If there is a chance that m doesn't have at least 1 of each of c(-1,0,1) then force them into the table with table(row(m), factor(m, levels=c(-1,0,1))) Bill Dunlap TIBCO Software Inc - Spotfire Division wdunlap tibco.com [R] Summarizing each row into a frequency table Daren Tan darentan76 at gmail.com Tue Mar 24 01:46:21 CET 2009 I have a matrix containing -1, 0, 1, however certain rows will not have all 3 numbers. I have written some codes to compute the frequency table of how many -1s, 0s, 1s per row, but it is very ugly and not efficient if there are more than 3 numbers. Please suggest. m - rbind(sample(0:1, replace=T, 10), sample(-1:1, replace=T, 10)) m.table - t(apply(m, 1, function(x) c(sum(x==-1, na.rm=T), sum(x==0, na.rm=T), sum(x==1, na.rm=T)) )) m.table - prop.table(m.table, 1)*100 colnames(m.table) - -1:1 __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
Re: [R] Why na.rm=FALSE is the default
The only reference that I can think of (a bit subtle/indirect) is: http://www.burns-stat.com/pages/Tutor/spreadsheet_addiction.html (look in the section on Propagation of Blanks). But I think that it really comes down to the following 2 variations on a rule: 1. Important decisions (such as throwing away information) should be made by a human not a computer 2. Important decisions (such as throwing away information) should be made by a person familiar with the data and scientific question, not by a programmer separated in time and space from the real question who was unlikely to be able to anticipate every situation. -- Gregory (Greg) L. Snow Ph.D. Statistical Data Center Intermountain Healthcare greg.s...@imail.org 801.408.8111 -Original Message- From: r-help-boun...@r-project.org [mailto:r-help-boun...@r- project.org] On Behalf Of Adam D. I. Kramer Sent: Tuesday, March 24, 2009 12:24 PM To: r-help@r-project.org Subject: [R] Why na.rm=FALSE is the default Dear Colleagues, I've been searching for a post or article or something which explains why having na.rm=FALSE or na.action=na.fail as the default is a better choice than TRUE or na.omit. I understand the basic argument: it does not make sense to average a nonexistance into an aggregate, and removing them implicitly leads to accidental pairwise deletion in some cases, and sum(x) / length(x) mean(x) (which many would find disturbing)...I'm just looking for a source to cite on this issue to support mimicking R's behavior in a database system's aggregating functions (sum, avg, var, etc.). Cordially, Adam Kramer Ph.D. Candidate, Social Psychology University of Oregon adik at uoregon dot edu __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting- guide.html and provide commented, minimal, self-contained, reproducible code. __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
Re: [R] read in large data file (tsv) with inline filter?
Hi all, Thanks a lot for your responses. I forgot to mention in my posting that I also want to try to be as cross-platform as possible (and thus to avoid relying on external calls to UNIX programs such as grep). I like the idea from Thomas: You certainly don't want to use repeated reads from the start of the file with skip=, but if you set up a file connection fileconnection - file(my.tsv, open=r) you can read from it incrementally with readLines() or read.delim() without going back to the start each time. But doing this (with the required calls to grep()) is *MUCH* slower than piping the file through UNIX grep -- so I think I will end up just sticking with that option and just ask Windows users install grep in order to use my software. --David *David J Reiss, PhD http://dreiss.isb.googlepages.com* Senior Research Scientist, Computational Biology, Baliga Labhttp://baliga.systemsbiology.net/ Institute for Systems Biology http://www.systemsbiology.org 1441 N 34th St., Seattle, WA 98103 (USA) On Tue, Mar 24, 2009 at 5:12 AM, Dirk Eddelbuettel e...@debian.org wrote: Hi David, On 23 March 2009 at 15:09, Dylan Beaudette wrote: | On Monday 23 March 2009, David Reiss wrote: | I have a very large tab-delimited file, too big to store in memory via | readLines() or read.delim(). Turns out I only need a few hundred of those | lines to be read in. If it were not so large, I could read the entire file | in and grep the lines I need. For such a large file; many calls to | read.delim() with incrementing skip and nrows parameters, followed by | grep() calls is very slow. I am aware of possibilities via SQLite; I would | prefer to not use that in this case. | | My question is...Is there a function for efficiently reading in a file | along the lines of read.delim(), which allows me to specify a filter (via | grep or something else) that tells the function to only read in certain | lines that match? | | If not, I would *love* to see a filter parameter added as an option to | read.delim() and/or readLines(). | | How about pre-filtering before loading the data into R: | | grep -E 'your pattern here' your_file_here your_filtered_file | | alternatively if you need to search in fields, see 'awk', and 'cut', or if you | need to delete things see 'tr'. | | These tools come with any unix-like OS, and you can probably get them on | windows without much effort. Also note that read.delim() and friends all read from connections, and 'piped expressions' (in the Unix shell command sense) can provide a source. That way you can build an ad-hoc filter extension by running readLines() over a pipe() connection. Consider this trivial example of grepping out Section headers from the R FAQ. We get everything double because of the Table of Contents and the actual section headers: R readLines( pipe(awk '/^[0-9+] / {print $1, $2, $3}' src/debian/R/R-alpha.20090320/doc/FAQ) ) [1] 1 Introduction 2 R Basics 3 R and 4 R Web [5] 5 R Add-On 6 R and 7 R Miscellanea 8 R Programming [9] 9 R Bugs1 Introduction 2 R Basics 3 R and [13] 4 R Web 5 R Add-On 6 R and 7 R Miscellanea [17] 8 R Programming 9 R Bugs R The regexp is simply 'digits at start of line followed by space' which skips subsections like 1.1, 1.2, ... Hth, Dirk -- Three out of two people have difficulties with fractions. [[alternative HTML version deleted]] __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
[R] modelling probabilities instead of binary data with logistic regression
Dear all, I have a dataset where I reduced the dimensionality, and now I have a response variable with probabilities/proportions between 0 and 1. I wanted to do a logistic regression on those, but the function glm refuses to do that with non-integer values in the response. I also tried lrm, but that one interpretes the probabilities as different levels and gives for every level a different intercept. Not exactly what I want... Is there a way to specify that the response variable should be interpreted as a probability? Kind regards Joris [[alternative HTML version deleted]] __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
[R] Probability trees
How can I create probability trees in R? I've searched everywhere I could and still have no clue. :-/ [[alternative HTML version deleted]] __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
[R] segfault when running heatmap()
Hi, I was wondering if someone in the mailing list has any insight into this segfault error that I consistently find when running a script containing heatmap() in R 2.8.1 and 2.8.0 on a Linux 64-bit machine. Some points: 1. This occurs when running heatmap(). 2. Interestingly, if I source() the script or copy and paste the script in its entirety, this error occurs. However, if I run the commands individually, heatmap() will actually work. 3. I've had this error occur on two types of machines as follows. Intel 64bit, linux kernel 2.6.18-92.1.22.el5, gcc version 4.1.2 as well as AMD 64bit, linux kernel 2.6.9-5.ELsmp, gcc version 3.4.3 Here is the error messages that I receive when I debug(heatmap) and source() the script containing heatmap(). The sessionInfo() follows. Browse[1] debug: op - par(no.readonly = TRUE) Browse[1] *** caught segfault *** address 0x103c93d53, cause 'memory not mapped' Traceback: 1: function (display = , width, height, pointsize, gamma, bg, canvas, fonts, xpos, ypos, title, type, antialias) {if (display == .Platform$GUI == AQUA is.na(Sys.getenv(DISPLAY, NA))) Sys.setenv(DISPLAY = :0)new - list()if (!missing(display)) new$display - displayif (!missing(width)) new$width - width if (!missing(height)) new$height - heightif (!missing(gamma)) new$gamma - gammaif (!missing(pointsize)) new$pointsize - pointsizeif (!missing(bg)) new$bg - bg if (!missing(canvas)) new$canvas - canvasif (!missing(xpos)) new$xpos - xposif (!missing(ypos)) new$ypos - yposif (!missing(title)) new$title - titleif (!checkIntFormat(new$title)) stop(invalid 'title')if (!missing(type)) new$type - match.arg(type, c(Xlib, cairo, nbcairo))if (!missing(antialias)) {new$antialias - pmatch(antialias, c(default, none, gray, subpixel)) if (is.na(new$antialias)) stop(invalid value for 'antialias')}d - check.options(new, name.opt = .X11.Options, envir = .X11env)type - if (capabilities(cairo)) switch(d$type, cairo = 1, nbcairo = 2, 0)else 0if (display == XImage) type - 0.Internal(X11(d$display, d$width, d$height, d$pointsize, d$gamma, d$colortype, d$maxcubesize, d$bg, d$canvas, d$fonts, NA_integer_, d$xpos, d$ypos, d$title, type, d$antialias))}() 2: par(no.readonly = TRUE) 3: heatmap(selected.matrix, distfun = cor.dist, zlim = zlim, col = colors.for.heatmap) 4: eval.with.vis(expr, envir, enclos) 5: eval.with.vis(ei, envir) Here is the sessionInfo() sessionInfo() R version 2.8.1 (2008-12-22) x86_64-unknown-linux-gnu locale: LC_CTYPE=en_US.UTF-8;LC_NUMERIC=C;LC_TIME=en_US.UTF-8;LC_COLLATE=en_US.UTF-8;LC_MONETARY=C;LC_MESSAGES=en_US.UTF-8;LC_PAPER=en_US.UTF-8;LC_NAME=C;LC_ADDRESS=C;LC_TELEPHONE=C;LC_MEASUREMENT=en_US.UTF-8;LC_IDENTIFICATION=C attached base packages: [1] tools grid stats graphics grDevices utils datasets [8] methods base other attached packages: [1] u133x3p.db_2.2.5RSQLite_0.7-1 DBI_0.2-4 [4] AnnotationDbi_1.4.3 Biobase_2.2.2 vcd_1.2-3 [7] colorspace_1.0-0MASS_7.2-46 Thanks, Andrew [[alternative HTML version deleted]] __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
Re: [R] Testing for symbolic links
On 25/03/2009, at 6:29 AM, Gregoire Pau wrote: Hello, How can I test in R whether a file is a symbolic link or not ? I haven't found anything relevant in R-help but I may be wrong. Thanks ! Since symbolic links are a Unix thing, I assume you are working on a system that is sufficiently Unix-like for the following roll-your-own to work: cfsl - function(file) { # cfsl -- check for symbolic link xxx - system(paste(ls -l,file),intern=TRUE) if(substr(xxx,1,1)==l) TRUE else FALSE } HTH cheers, Rolf Turner ## Attention:\ This e-mail message is privileged and confid...{{dropped:9}} __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
Re: [R] modelling probabilities instead of binary data with logistic regression
Thank you all for the very fast answers. My proportions come from a factor analysis on a number of binary variables, in order to avoid having to fit 12 logistic regressions on the same dataset. By scaling the obtained scores to 0 and 1, I get weighted averages of the response combinations I'm interested in. I tried the betareg function, but that one can't deal with probabilities 0 and 1 unfortunately. I'll have to manually do the logit transformation, I'm afraid. Thanks for the help. Kind regards Joris On Tue, Mar 24, 2009 at 8:48 PM, Kjetil Halvorsen kjetilbrinchmannhalvor...@gmail.com wrote: You did'nt say how your proportions have arisen! If each corresonds to one observation, you could simply simulate indicator variables with those proportions as prob's, fit glm, repeat many times, and average results! More seriously, you could transform the proportions to logits logit - log(p/(1-p)) and fit a linear regression. Kjetil On Tue, Mar 24, 2009 at 3:30 PM, joris meys jorism...@gmail.com wrote: Dear all, I have a dataset where I reduced the dimensionality, and now I have a response variable with probabilities/proportions between 0 and 1. I wanted to do a logistic regression on those, but the function glm refuses to do that with non-integer values in the response. I also tried lrm, but that one interpretes the probabilities as different levels and gives for every level a different intercept. Not exactly what I want... Is there a way to specify that the response variable should be interpreted as a probability? Kind regards Joris [[alternative HTML version deleted]] __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code. [[alternative HTML version deleted]] __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
[R] Green and Byar (1980) Prostate Cancer Data set from Andrews and Herzberg - Data
Hi, I am looking for a data set containing the information from a randomized trial evaluating the effect of DES (diethylsilbestrol) on multiple time-to-event endpoints, prostate cancer, CVD, and other causes. The original source of this data is Green and Byar (1980). This is a popular competing risks problem that has subsequently been discussed in a number of statistical papers including Kay (1986). Does anyone have a digital version of this data set? This data is also presented in Andrews, D. F. and Herzberg, A. M. (1985). Data. Does a digital version of all the data sets in A H exist? Thanks very much, Ravi. Ravi Varadhan, Ph.D. Assistant Professor, Division of Geriatric Medicine and Gerontology School of Medicine Johns Hopkins University Ph. (410) 502-2619 email: rvarad...@jhmi.edu __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
[R] Executing an external executable from within R?
For example, from within an R script I would like to be able to launch NotePad.exe. Is there an R call for launching Notepad.exe from within R? I've tried the following, but they don't seem to work: system(paste('C:/WINDOWS/NOTEPAD.exe'), wait = FALSE) system(C:/WINDOWS/NOTEPAD.exe, wait = FALSE) system(NOTEPAD, wait = FALSE) That is, these do not bring up the Notepad GUI. Thanks for any insights. __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.