Re: [R] help_transformation

On Wed, 25 Jun 2008, Moshe Olshansky wrote: Let F be the distribution function of Y, PSI the standard normal distribution anf IPSI it's inverse. Let f(x) = IPSI(F(x)). It is not difficult to see that f(Y) has standard normal distribution. So you can replace F with the empirical distribution an

Re: [R] help_transformation

Let F be the distribution function of Y, PSI the standard normal distribution anf IPSI it's inverse. Let f(x) = IPSI(F(x)). It is not difficult to see that f(Y) has standard normal distribution. So you can replace F with the empirical distribution and IPSI is the qnorm function of R. --- On We

Re: [R] R help

Hi, Thank u so much for resolving my problem Ramya -- View this message in context: http://www.nabble.com/R-help-tp18121494p18126036.html Sent from the R help mailing list archive at Nabble.com. __ R-help@r-project.org mailing list https://stat.et

Re: [R] How to turn Time Series daily values into weekly means (aggregate?)

That is so simple, and works wonderfully! The best place to hide things is right in front of my face. thanks agian stephen On Wed, Jun 25, 2008 at 10:24 PM, jim holtman <[EMAIL PROTECTED]> wrote: > Try this: > > y.ts <- ts(y, frequency=7) # make data weekly > aggregate(y.ts, FUN=mean) > > to g

Re: [R] How to turn Time Series daily values into weekly means (aggregate?)

Try this: y.ts <- ts(y, frequency=7) # make data weekly aggregate(y.ts, FUN=mean) to get your 15 minute readings into a day, this should work: y.ts <- ts(y, frequency=96) aggregate(y.ts, FUN=mean) This is fine as long as everything is evenly spaced. It might be better if you had the time of t

[R] How to turn Time Series daily values into weekly means (aggregate?)

#this is a daily series of precipitation data. I would like to condense it into weekly means. How can I do this #as a side note I would like to do this same thing to two years worth of fifteen minute interval data and make it into #a series of daily averages (there are 96 readings per day) #is ag

Re: [R] dgamma in WinBUGS and JAGS (rjags)

Seyed Reza Jafarzadeh gmail.com> writes: > > Hello, > > In WinBUGS 1.4 manual > (http://www.mrc-bsu.cam.ac.uk/bugs/winbugs/manual14.pdf), the gamma > density is presented as dgamma(r,mu) where r and mu are the shape and > rate parameters, respectively. In JAGS (rjags) manual version 1.0.2, > Ma

Re: [R] data frame manipulation - splitting monitoring interval and assigning stage

Is this what you want: > x <- read.table(textConnection("Check1 Check2 HatchDate + 101 121 110 + 130 150 140 + 140 150 160"), header=TRUE) > closeAllConnections() > x Check1 Check2 HatchDate 1101121 110 2130150 140 3140150

Re: [R] xyplot questions - axis and plotting two things in same panel

On 6/25/08, Franz Mueter <[EMAIL PROTECTED]> wrote: > As for your first problem, try: > > xyplot(numbers~breaks|moltype, groups = type, data = alldata, type = "l") > > > -Original Message- > From: [EMAIL PROTECTED] [mailto:[EMAIL PROTECTED] On > Behalf Of Karin Lagesen > Sent: Wednesda

Re: [R] R alternative to SAS PROC REPORT

Philip Twumasi-Ankrah wrote: R has wonderful graphics but I am wondering whether there is anything in R to provide customization of tables like PROC Report does in SAS. You can do far better than PROC REPORT. See for example http://biostat.mc.vanderbilt.edu/twiki/pub/Main/StatReport/summary

Re: [R] Find max of a row in data frame (like Excel)

Thanks all. I got the result I wanted. I appreciate all the pointer. I never fully understand the apply function, as well as the lapply. And this occasion is one of those where these functions comes in to play. On Wed, Jun 25, 2008 at 2:10 PM, Kenn Konstabel <[EMAIL PROTECTED]> wrote: > apply max

Re: [R] help with cube3d cube size

Thanks for the pointers. I think the package is great, just want to use it to its full potential without driving the list crazy with questions. Below is my output to help and sessionInfo(). I don't see the scaling functions, although I now see that they can be retrieved with ?matrices. You guys ar

[R] Use plotmath expressions read from a text file in mtext/bquote

Hello R-help List I am writing some R scripts to create graphs of water quality trends that will be called by a web service running R. The axis titles will need to change as the input data (ie. water quality variable) changes according to a user's choice made via a web page. The way I am current

[R] Reminder about R 'chat room'...

If you like using IRC, then you might like to try the channel devoted to R: irc://irc.freenode.net/#R You can go there to ask all your R related questions! -- MetaBase - http://BioDatabase.Org [[alternative HTML version deleted]] __ R-help@r

Re: [R] R help

On Wed, Jun 25, 2008 at 01:06:48PM -0700, [EMAIL PROTECTED] wrote: > Geneset.ls <- list() > for(i in 1: 5452) > { > Geneset.ls[[i]] <- read.delim("c.all.v2.5.symbols.gmt", header=T, skip=1, > sep="\t") > } > > I have a file named c.all.v2.5.symbols.gmt.it is a huge file with > about 30 columns a

Re: [R] help with cube3d cube size

Mark Kimpel wrote: Ben and Duncan, Thanks for your helpful suggestions. I"m having some difficulty navigating this really good package using my normal learning techniques. When I do 'help(package = "rgl") it seems only a very small subset of functions available show up. I think the full list s

Re: [R] Is this sapply behaviour normal?

Rolf Turner wrote: > > The answer to your question is ``yeah, sort of''. The reason for the > difference is that mean() is generic and has a method for data frames, > according to which the mean of each column of the data frame is found > in some ``appropriate'' manner. (Essentially the columns o

Re: [R] Find max of a row in data frame (like Excel)

apply max to columns f1...f4 and assign it to rs$f: rs$f <- apply(rs[,paste("f",1:4,sep="")],1,max) or rs$f <- apply(rs[,2:5],1,max) On Wed, Jun 25, 2008 at 1:41 AM, Anh Tran <[EMAIL PROTECTED]> wrote: > Hi, > Here's the data we have: > > > rs[1:5,] >probe_id f1 f2 f3 f4 M

[R] R help

hi, I have a question could please help me. Geneset.ls <- list() for(i in 1: 5452) { Geneset.ls[[i]] <- read.delim("c.all.v2.5.symbols.gmt", header=T, skip=1, sep="\t") } I have a file named c.all.v2.5.symbols.gmt.it is a huge file with about 30 columns and 5452 rows. I want to write single r

Re: [R] xyplot questions - axis and plotting two things in same panel

As for your first problem, try: xyplot(numbers~breaks|moltype, groups = type, data = alldata, type = "l") -Original Message- From: [EMAIL PROTECTED] [mailto:[EMAIL PROTECTED] On Behalf Of Karin Lagesen Sent: Wednesday, June 25, 2008 2:13 AM To: r-help@r-project.org Subject: [R] xyplot que

Re: [R] Is this sapply behaviour normal?

The answer to your question is ``yeah, sort of''. The reason for the difference is that mean() is generic and has a method for data frames, according to which the mean of each column of the data frame is found in some ``appropriate'' manner. (Essentially the columns of the data frame must be ei

Re: [R] Is this sapply behaviour normal?

On Wed, Jun 25, 2008 at 6:00 PM, Victor Homar <[EMAIL PROTECTED]> wrote: > > Hi, I'm trying to use sapply to compute the min of several variables, > each > of them stored in data.frames, grouped as a list: > Is it normal that mean() and min() produce different objects dimensions? > it is ex

Re: [R] Using metric units in plots

On Fri, 20-Jun-2008 at 01:08PM +0100, Gavin Simpson wrote: |> But it is not too difficult to do this yourself: |> |> in2cm <- function(x) return(x * 2.54) |> |> cm2in <- function(x) return(x * 0.3937008) |> |> then use in2cm() or cm2in() depending on what you want to achieve. If |> you want a

Re: [R] running R-code outside of R

Thanks to all of the responders. It looks like dreams may come true after all :-) The application is as follows. Respondents fill out a questionnaire that has been posted online. Output is in excel or text format. My client (typically working for a government agency that provides subsidies t

Re: [R] R alternative to SAS PROC REPORT

Example- I don't know SAS well, or at all at this point. But, if I knew what you wanted maybe I could help you. thanks Stephen On Wed, Jun 25, 2008 at 3:32 PM, Philip Twumasi-Ankrah < [EMAIL PROTECTED]> wrote: > R has wonderful graphics but I am wondering whether there is anything in R > to pro

[R] strange imaging issues

It seems that just recently my plot outputs are getting messed up. Currently I am only getting the plotted points and the bottom axis. I am getting no text and no side axis. As far as I know nothing got changed on the server. I have tested this with simple plots and with plots that have heading

Re: [R] running R-code outside of R

If I analyze a client's data using an R script I created then I can charge the client a $20,000 consulting fee, but, if I let the client push the button to execute the R script and charge him 10 cents for the privilege then I can be sued for violating the GPL? Or are my I think you cannot be su

[R] R alternative to SAS PROC REPORT

R has wonderful graphics but I am wondering whether there is anything in R to provide customization of tables like PROC Report does in SAS. A Smile costs Nothing  But Rewards Everything Happiness is not perfected until it is shared   

[R] Equivalence test...

Dear helpeRs: I am writting you because I have some doubts in relation to the equivalence test. I am interested in compare seed set of treated plants and control plants. I used the tost command in R, and the value of epsilon that I put was the standard deviation of the control sample. In all ca

[R] Goodness-of-fit for zero-truncated poisson distribution

Hi there, I am trying to write a function to perform GOF test of data to a zero-truncated Poisson distribution. I am facing 2 problems. 1) How can I obtain a frequency table for all values within the range of observed values? For instance if the observations are obs <- c("A", "A", "A", "A", "B",

Re: [R] logistic regression

Sorry for flooding this forum, but I think I've realised that I need to do multinomial logistic regression for my problem... Would be interested in your opinion as to whether this is actually any better than running three binomial logistic regressions separately.. Thanks M On Wed, Jun 25, 2008 at

[R] Is this sapply behaviour normal?

Hi, I'm trying to use sapply to compute the min of several variables, each of them stored in data.frames, grouped as a list: Is it normal that mean() and min() produce different objects dimensions? > str(dats) List of 5 $ log20:'data.frame': 83 obs. of 5 variables: ..$

[R] pvclust:a general and a specific question

I realize questions about packages should go to the package maintainer, but perhaps I have an old email address ([EMAIL PROTECTED]) Also I have both a general, and a specific, question. 1) General question: i've used pvclust before to assess significance of clusters and got reasonable results. How

[R] dgamma in WinBUGS and JAGS (rjags)

Hello, In WinBUGS 1.4 manual (http://www.mrc-bsu.cam.ac.uk/bugs/winbugs/manual14.pdf), the gamma density is presented as dgamma(r,mu) where r and mu are the shape and rate parameters, respectively. In JAGS (rjags) manual version 1.0.2, May 9, 2008 (http://www-fis.iarc.fr/~martyn/software/jags/jags

[R] R/S-Plus Fundamentals and Programming Techniques course in *** New YorkCity *** July 28-29 by XLSolutions Corp

Our July *** New York City *** R/S-Plus Fundamentals and Programming Techniques course is scheduled for: New York City / July 28-29, 2008 *** Please direct enquiries to Sue Turner: [EMAIL PROTECTED] Payment due AFTER the class Ask for Group Discount --- Looking for R Advanc

Re: [R] Hessian in box-constraint problem - concern OPTIM function

The description of your problem is too complex for me to analyze in the time I have available for this. Could you develop a very brief, simple example that illustrates your question? A very brief Monte Carlo, estimating 2 parameters in a very simple formula with one of the parameters at

Re: [R] expression, strsplit, ...

Try this: plot(1, xlab = ~ alpha / V * m^-3 * kg ^-2 * l^4) On Wed, Jun 25, 2008 at 1:06 PM, baptiste Auguié <[EMAIL PROTECTED]> wrote: > DeaR list, > > I'm a bit lost in the behavior of substitute and co. > I often use fairly long axis labels in my graphs (long to write, that is). > Typically,

[R] rearrange data

Dear HelpeRs, i have a data.frame df as follows: > df <- data.frame(id=rep(1:3,rep(10,3)), emoqu=as.factor(rep(c(0,0,1,1,2,2,3,3,4,4),3)), x=rnorm(30), y=runif(30)) Now, I would like to rearrange the data and it works - regarding the variables/columns I would l

[R] data frame manipulation - splitting monitoring interval and assigning stage

Hello, everyone. I'm hoping to prevent myself from doing a lot of pointing and clicking in Excel. I have a dataframe of bird nest check observations, in which I know the date of the first check, the date of the second check (both currently in Julian date format), the status of the nest at the seco

Re: [R] stringdot

I tried the following data(promotergene) ## train svm using custom kernel stringkernel<-stringdot(length = 4, lambda = 0.5, type = "sequence", normalized = TRUE) gene <- ksvm(Class~.,data=promotergene,kernel=stringkernel,C=10,cross=5) I get the following error cannot allocate vector of size 1.

[R] expression, strsplit, ...

DeaR list, I'm a bit lost in the behavior of substitute and co. I often use fairly long axis labels in my graphs (long to write, that is). Typically, they would contain some greek letters and units with exponents, as in: xlab=expression(paste("text ", alpha, " / ", V,".", m^{-3}, ".", kg

Re: [R] selecting values that are unique, instead of selecting unique values

On Wed, 25 Jun 2008, Gabor Csardi wrote: Wow, that is smart, although is seems to be overkill. I guess 'duplicated' is better than O(n^2), is it really? Yes as it hashes, but the overhead on short vectors is high since it always hashes. Gabor On Wed, Jun 25, 2008 at 05:43:30PM +0100,

Re: [R] running R-code outside of R

Spencer Graves wrote: If you want to hide the fact that you are using R -- especially if you charge people for your software that uses R clandestinely -- that's a violation of the license (GPL). No on both accounts .. but thanks for pointing this out none the less.

Re: [R] selecting values that are unique, instead of selecting unique values

Wow, that is smart, although is seems to be overkill. I guess 'duplicated' is better than O(n^2), is it really? Gabor On Wed, Jun 25, 2008 at 05:43:30PM +0100, Prof Brian Ripley wrote: > On Wed, 25 Jun 2008, Marc Schwartz wrote: > >> on 06/25/2008 11:19 AM Daren Tan wrote: >>> >>> unique(c(1

Re: [R] selecting values that are unique, instead of selecting unique values

On Wed, Jun 25, 2008 at 12:19 PM, Daren Tan <[EMAIL PROTECTED]> wrote: > > > unique(c(1:10,1)) gives 1:10 (i.e. unique values), is there any method to get > only 2:10 (i.e. values that are unique) ? > > Try this: setdiff(x, x[duplicated(x)]) __ R-help

Re: [R] selecting values that are unique, instead of selecting unique values

on 06/25/2008 11:44 AM Gabor Csardi wrote: I'm sorry to say, but this one is wrong, too. Maybe coffee really helps, I just had one. :) Vec <- c(20:30,20) which(table(Vec) == 1) 21 22 23 24 25 26 27 28 29 30 2 3 4 5 6 7 8 9 10 11 You would actually need the names, but that would invo

Re: [R] selecting values that are unique, instead of selecting unique values

I'm sorry to say, but this one is wrong, too. Maybe coffee really helps, I just had one. :) > Vec <- c(20:30,20) > which(table(Vec) == 1) 21 22 23 24 25 26 27 28 29 30 2 3 4 5 6 7 8 9 10 11 You would actually need the names, but that would involve some numberic -> character -> numeric

Re: [R] selecting values that are unique, instead of selecting unique values

On Wed, 25 Jun 2008, Marc Schwartz wrote: on 06/25/2008 11:19 AM Daren Tan wrote: unique(c(1:10,1)) gives 1:10 (i.e. unique values), is there any method to get only 2:10 (i.e. values that are unique) ? The easiest might be: Vec [1] 1 2 3 4 5 6 7 8 9 10 1 Vec[table(Vec) == 1]

Re: [R] selecting values that are unique, instead of selecting unique values

Hmmm, this is not very good: > Vec <- c(10:1,1) > Vec[ table(Vec) == 1 ] [1] 9 8 7 6 5 4 3 2 1 and these are obviously not the unique values. This one is better: Vec [ ! duplicated(Vec) & ! duplicated(Vec, fromLast=TRUE) ] Gabor On Wed, Jun 25, 2008 at 11:29:31AM -0500, Marc Schwartz wrote

Re: [R] LDA on pre-assigned training and testing data sets

I think this line mafdiscpred <- predict(mafdisc, data = test) needs to be mafdiscpred <- predict(mafdisc, newdata = test) Michael Conklin Chief Methodologist - Advanced Analytics MarketTools, Inc. 6465 Wayzata Blvd. Suite 170 Minneapolis, MN 55426 Tel: 952.417.4719 | Mobile:612.20

Re: [R] selecting values that are unique, instead of selecting unique values

on 06/25/2008 11:29 AM Marc Schwartz wrote: on 06/25/2008 11:19 AM Daren Tan wrote: unique(c(1:10,1)) gives 1:10 (i.e. unique values), is there any method to get only 2:10 (i.e. values that are unique) ? The easiest might be: > Vec [1] 1 2 3 4 5 6 7 8 9 10 1 > Vec[table(Vec) =

Re: [R] selecting values that are unique, instead of selecting unique values

on 06/25/2008 11:19 AM Daren Tan wrote: unique(c(1:10,1)) gives 1:10 (i.e. unique values), is there any method to get only 2:10 (i.e. values that are unique) ? The easiest might be: > Vec [1] 1 2 3 4 5 6 7 8 9 10 1 > Vec[table(Vec) == 1] [1] 2 3 4 5 6 7 8 9 10 HTH, Marc

[R] LDA on pre-assigned training and testing data sets

Dear r-help I am trying to run LDA on a training data set, and test it on another data set with the same variables. I found examples using crossvalidation, and using training and testing data sets set up with sample, but not when they are preassigned. Here is what I tried # FIRST SET UP A DA

Re: [R] unstructured correlation matrix in lme

I would like to make clear that the SAS "unstructured" correlation matrix in the second model was : Estimated R Correlation Matrix for id 1 1 1. 0.8575 0.6984 0.4657 0.3165 2 0.8575 1. 0.8557 0.5670 0.4039 3 0.6984 0.8557 1.0

Re: [R] Need ideas on how to show spikes in my data and how to code it in R

I don't understand this. Why not just get hist() to plot on the density scale, thereby making its output commensurate with the output of density()? The hist() function will plot on the density scale if you ask it to. Set freq=FALSE (or prob=TRUE) in the call to hist. ehrm

[R] selecting values that are unique, instead of selecting unique values

unique(c(1:10,1)) gives 1:10 (i.e. unique values), is there any method to get only 2:10 (i.e. values that are unique) ? _ Easily edit your photos like a pro with Photo Gallery. [[alternative HTML version deleted]] _

[R] unstructured correlation matrix in lme

Hello R users, I'm student and I'm actually having a lecture introducing repeated mesures analysis. Unfortunately, all examples use SAS system... I'm working with lme function (package "nlme"), and I'm using extract.lme.cov (package "mgcv") to extract covariance structure of models. One example

Re: [R] running R-code outside of R

on 06/25/2008 10:28 AM Michael Conklin wrote: Spencer Graves wrote: If you want to hide the fact that you are using R -- especially if >you charge people for your software that uses R clandestinely -- that's a >violation of the license (GPL). I doubt if anyone associated with R would >bo

Re: [R] running R-code outside of R

I am not an expert nor a lawyer but ... On Wed, Jun 25, 2008 at 5:28 PM, Michael Conklin <[EMAIL PROTECTED]> wrote: > > Spencer Graves wrote: > >> If you want to hide the fact that you are using R -- especially > if >you charge people for your software that uses R clandestinely -- > that's a

Re: [R] running R-code outside of R

Some clarifications. R's license (GPL v2) is not about money, you can charge anyone as much as you wish. If you create an R program (and don't modify R itself), then you can distribute that program according to any license you wish. If you modify R itself _and_ distribute the modified version,

Re: [R] help with cube3d cube size

Ben and Duncan, Thanks for your helpful suggestions. I"m having some difficulty navigating this really good package using my normal learning techniques. When I do 'help(package = "rgl") it seems only a very small subset of functions available show up. Perusing the rgl.pdf downloaded from CRAN demo

[R] confidence bounds using contour plot

Hello I'm trying to calculate 2d confindence bounds into a scatterplot using the function "kde2d" (package MASS) and a contour plot. I found a similar post providing a solution - unfortunatly I do not realy understand which data I have to use to calculated the named "quantile": Post URL: http://

Re: [R] T and P Statistics

Hi, help(t.test) x = rnorm(10, mean = 10, sd = 1) #some data mytest = t.test(x, mu = 10) #is mu = 10 attributes(mytest) #what's in the test mytest$p.value #obtain the p-value mytest$statistic #obtain the t-value aka statistic HTH Thomas K

Re: [R] running R-code outside of R

Spencer Graves wrote: > If you want to hide the fact that you are using R -- especially if >you charge people for your software that uses R clandestinely -- that's a >violation of the license (GPL). I doubt if anyone associated with R would >bother with a lawsuit, but a competitor who offer

[R] subscripted assignments errormessage in gap.boxpot

I am trying to create a boxplot that has a gap with different scales so that my boxes actually show (compare attachments). I have referred to the help pages for gap.boxplot, gap.plot, list with no luck so far. Here is my script and the resulting error message: # Import *.csv files containing ar

Re: [R] tiff()-bug (was re:Preparing high quality figures

Hi, I don't know if this matters but it worked for me with no problems …. > sessionInfo() R version 2.7.0 (2008-04-22) i386-pc-mingw32 locale: LC_COLLATE=English_United States.1252;LC_CTYPE=English_United States.1252;LC_MONETARY=English_United States.1252;LC_NUMERIC=C;LC_TIME=English_Unit

Re: [R] tiff()-bug (was re:Preparing high quality figures with, tiff as end result)

To the R colleagues, I do not have any problems when running this code, everything works well: tiff() plot(1:1000) dev.off() I am using R 2.7.1 and Windows XP Professional (service pack 2). Regards, Paulo Barata --- Paulo B

Re: [R] a loop....

> I recommend avoid loop in this case > I'm working with many files... I must utilise a loop necessarily. > And you shall know that R is pretty smart in handling missing values. How > do you know after change NA -> 0 that 0 is from NA and not > like in 1994 row and second column. This isn't a

Re: [R] running R-code outside of R

If you want to hide the fact that you are using R -- especially if you charge people for your software that uses R clandestinely -- that's a violation of the license (GPL). I doubt if anyone associated with R would bother with a lawsuit, but a competitor who offers related software might.

[R] Memory allocation failed: Copying Node

Following code bugs with "Memory allocation failed: Copying Node" error after parsing n thousand files. I have included the main code(below) and functions(after the main code). I am not sure which lines are causing the copying Node which results in memory failure. Please advise. #Beginning

Re: [R] loop with files

Hi, I am not sure this is what you want …. But alist <- list.files(path = "whatever path you have for your files", full.names = TRUE) Now you have a list with the names of your files …. Form each name you can make a variable name and assign that file …. fname <- substring(alist[i], first, l

Re: [R] Accessing Named Column in a Matrix

On Mon, Jun 23, 2008 at 9:12 PM, Gundala Viswanath <[EMAIL PROTECTED]> wrote: > I've also tried with > > data$var > > But still fail to access "var" column > you can't use $ with matrices (see help("$") !), but you can use [ with names, or convert you matrix to a data frame: myData[, "var"]

[R] Extract naiveBayes details

Hey, I just like to know how to extract details from the naiveBayes model (package e1071). I mean, for each possible value the model defines how much it influences the outcome. I want to sort those probabilities and show the values with the highest impact. How could I do that? PS: I tried using

[R] help_transformation

heya, i am fitting linear mixed effect model to a response Y. Y shows an s-shaped distribution when using QQ-plots (some zero values and some very high values). hence, which transformation should i apply that Y follows a normal distribution? any r-function/package available to do this? thanks

[R] xyplot questions - axis and plotting two things in same panel

Hi list! I am trying to use xyplot to plot some graphs. The data I have looks like this: > alldata[1:10,] breaks numbers moltypetype 1 0.0006598 5S Between species 2 0.407 0 5S Between species 3 0.8135228 5S Between species 4 1.2200

[R] Working with R in a Excel VBA

Hello EveryBody, I have some problems to connect R with Excel. It there somebody can help me to understand how to proceed. See you very soon -- View this message in context: http://www.nabble.com/Working-with-R-in-a-Excel-VBA-tp18109068p18109068.html Sent from the R help mailing list archive a

Re: [R] T and P Statistics

If you would have tried help.search("t-test") It would have listed the function t.test() ?t.test Will give you the helpfile with instructions. ir. Thierry Onkelinx Instituut voor natuur- en bosonderz

Re: [R] persp plot

Chad Junkermeier byu.edu> writes: > > I have a set of data in the form > x1, y1, z1 > x1, y2, z2 > ... > x1, yN, zN > x2, y1, z(N+1) > x2, y2, z(N+2) > ... > x2, yN, z(2N) > ...and so on... > xM, yN, val(M*N) > > Do you have any suggestions? Not at all carefully tested, but: ## make up dat

Re: [R] running R-code outside of R

Jim Porzak wrote: The user of your R script sees only the outputs you create. The R source is hidden. Ah .. that sounds great .. I wish I had known about this a month ago! I'll have to check it out - thanks! Esmail HTH, Jim Porzak <..> > Would the R script that is being run be hidden fr

Re: [R] tiff()-bug (was re:Preparing high quality figures with tiff as end result)

On 6/25/2008 9:37 AM, Gustaf Rydevik wrote: > A short update that may be of help: > The snippet of code does not crash R if i run under vanilla, nor if I > change R to MDI-mode. > It does crash R infallibly if I set it to SDI-mode in the Rprofile > file. Strange... It was an uninitialized variabl

[R] stringdot

Hi!! I am trying to figure out how to use the string kernel "stringdot" in kernlab. k <- function(x,y) { (sum(x*y) +1)*exp(-0.001*sum((x-y)^2)) } class(k) <- "kernel" data(promotergene) ## train svm using custom kernel gene.k <- ksvm(Class~.,data=promotergene,kernel=k,C=10,cross=5) # works

[R] T and P Statistics

How do you calculate T and P statistics (T- test) in R? Is there a package out there that can do these calculations? Best, Michael Tong Futures Associate Quantitative Research Services Franklin Templeton Investments, Inc. 600 Fifth Ave New York, NY 10020 (212) 632-4254 [EMAIL PROTECTED] N

Re: [R] I want to install a package on Max OS X from a local file

Macintosh OS X 10.5.3 R version 2.7 (binary distribution) #I tried this in R install.packages(file.choose(), repos=NULL, type="source") WARNING: omitting pointless dependence on 'R' without a version requirement Warning message: In install.packages(file.choose(), repos = NULL, type = "source") :

Re: [R] avoid using Dingbats symbols for points()

On 25 Jun 2008, at 15:22, Prof Brian Ripley wrote: Please look at the NEWS for R-devel, which was an option to work around this known bug in Adobe Illustrator. Thanks a lot for the hint. (Of course, the R posting guide suggested this for before posting.) I looked at several mailing lists

Re: [R] tiff()-bug (was re:Preparing high quality figures with tiff as end result)

A short update that may be of help: The snippet of code does not crash R if i run under vanilla, nor if I change R to MDI-mode. It does crash R infallibly if I set it to SDI-mode in the Rprofile file. Strange... /Gustaf On Wed, Jun 25, 2008 at 3:16 PM, Prof Brian Ripley <[EMAIL PROTECTED]> wro

Re: [R] gap.boxplot error message?

I don't believe so. Sorry if I am missing something (I am a beginner user of R). I tried just putting in all the defaults as see on http://bm2.genes.nig.ac.jp/RGM2/R_current/library/plotrix/man/gap.boxplot.html Here is a copy of my script and how the graph looks right now (without the break in

Re: [R] I want to install a package on Max OS X from a local file

On Wed, 25 Jun 2008, stephen sefick wrote: install.packages(file.choose(), repos=NULL) thought this would work, but it didn't the package is the sowas package - this doesn't seem to be a CRAN package, and it can be found at : You forgot a lot of things asked for in the posting guide, but if th

Re: [R] avoid using Dingbats symbols for points()

Please look at the NEWS for R-devel, which was an option to work around this known bug in Adobe Illustrator. (Of course, the R posting guide suggested this for before posting.) On Wed, 25 Jun 2008, Hans-Joerg Bibiko wrote: Hi, I came across with a tiny problem. E.g.: pdf() plot(1:5) points

Re: [R] tiff()-bug (was re:Preparing high quality figures with tiff as end result)

On Wed, 25 Jun 2008, Peng Jiang wrote: Hi , Gustaf i don't know why but it works pretty well on a mac. with completely different code. Gustaf Rydevik has mentioned this before -- it never fails for me on Windows and hence one would not expect there to be a change in 2.7.1. Only if someone c

Re: [R] gap.boxplot error message?

is there an na.rm argument in gap.boxplot? On Wed, Jun 25, 2008 at 11:24 AM, Megan J Bellamy <[EMAIL PROTECTED]> wrote: > Hi Stephen, > > I tried what you suggested and got a different error message instead... any > ideas? > > > gap.boxplot(CLI3, CLI4, CLI5, CLI6, CLI7, gap=list(top=c(8000,28

Re: [R] gap.boxplot error message?

Hi Stephen, I tried what you suggested and got a different error message instead... any ideas? > gap.boxplot(CLI3, CLI4, CLI5, CLI6, CLI7, gap=list(top=c(8000,28), > bottom=c(0,250)), range=50, outline=TRUE) Error in bxgap$out[bxgap$out > gap$top[2]] <- bxgap$out[bxgap$out > gap$top[2]] -

Re: [R] I want to install a package on Max OS X from a local file

no it didn't- am I missing something (Mac OS X 10.5.3, R 2.7) new-host-3:~ sefick$ R CMD INSTALL /Users/Desktop/sowas.tar.gz WARNING: invalid package '/Users/Desktop/sowas.tar.gz' * Installing to library '/Library/Frameworks/R.framework/Resources/library' ERROR: no packages specified On Wed, Jun

Re: [R] I want to install a package on Max OS X from a local file

From the (terminal window) command line try: R CMD INSTALL path.to.file/filename.tar.gz Does that do it? Richard stephen sefick wrote: install.packages(file.choose(), repos=NULL) thought this would work, but it didn't the package is the sowas package - this doesn't seem to be a CRAN package

Re: [R] logistic regression

Just a small correction to my previous reply. I meant to say probabilities of success for each type add up to one. thanks Frank for noticing the mistake. Bill.Venables wrote: > > It looks like A*B*C*D is a complete, totally saturated model, (the > residual deviance is effectively zero, and the

[R] Problems with Cairo-installation

Dear Everybody, install.packages("Cairo") returns [...] * Installing *source* package 'Cairo' ... checking for gcc... gcc-4.2 -std=gnu99 checking for C compiler default output file name... configure: error: C compiler cannot create executables See `config.log' for more details. ERROR: configuration

Re: [R] gap.boxplot error message?

the par(ask=FALSE) doesn't belong in the code (I think). gap.boxplot(CLI3, CLI4, CLI5, CLI6, CLI7, gap=list(top=c(8000,28), bottom=c(0,250)), range=50, outline=TRUE) but I haven't tried this. Stephen On Wed, Jun 25, 2008 at 10:49 AM, Megan J Bellamy <[EMAIL PROTECTED]> wrote: > Hello, > > Wh

Re: [R] I want to install a package on Max OS X from a local file

install.packages(file.choose(), repos=NULL) thought this would work, but it didn't the package is the sowas package - this doesn't seem to be a CRAN package, and it can be found at : http://tocsy.agnld.uni-potsdam.de/wavelets/ On Wed, Jun 25, 2008 at 8:25 AM, stephen sefick <[EMAIL PROTECTED]> wr

[R] gap.boxplot error message?

Hello, When I put in the following script line: gap.boxplot(CLI3, CLI4, CLI5, CLI6, CLI7, gap=list(top=c(8000,28), bottom=c(0,250)), range=50, outline=TRUE, par(ask=FALSE) I get a '+' telling me I am missing something. I have tried adding ')', 'width=NULL', etc and then I get this error: Er

[R] I want to install a package on Max OS X from a local file

I can't figure this one out- I am the administrator, The file that I want to install is a .tar.gz which is located on my desktop. How do I get it into my packages directory- through the GUI or through brute force? thanks stephen -- Let's not spend our time and resources thinking about things t

Re: [R] How to solve empty cells in the contingency table?

I think not considering the zero cells compromises the estimates you derive from you analysis. For instance, what will be the value of N used in the MLE estimation? You can ZIP - Zero Inflated Poisson which should provide you with the means to account for the zeros. R has funstions to do that.

  1   2   >