Re: [R] nnet
Please do not post repeatedly to multiple lists. (I have removed Bioconductor from this reply, and this repeats https://stat.ethz.ch/pipermail/r-help/2005-December/083391.html.) That output is not from nnet: the first 10 lines are trace msgs from nnet, but no nnet output is shown. (It looks like a confusion matrix, but only you know how you generated it.) See also the comments at the end of this reply. - The uncredited author of nnet On Wed, 21 Dec 2005, madhurima bhattacharjee wrote: Hello Everybody, I would like to know how to interpret the result of nnet function of R. My result looks like this: # weights: 24 initial value 6.533893 iter 10 value 4.616299 iter 20 value 4.616120 iter 30 value 4.616109 iter 30 value 4.616109 final value 4.616109 converged cres true 1 1 10 2 3 Can anyone please help me asap? Thanks and Regards, Madhurima. PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html That really does apply to you. -- Brian D. Ripley, [EMAIL PROTECTED] Professor of Applied Statistics, http://www.stats.ox.ac.uk/~ripley/ University of Oxford, Tel: +44 1865 272861 (self) 1 South Parks Road, +44 1865 272866 (PA) Oxford OX1 3TG, UKFax: +44 1865 272595 __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
Re: [R] Wilcoxon Mann-Whitney Rank Sum Test in R
On Wed, 21 Dec 2005, Peter Dalgaard wrote: P Ehlers [EMAIL PROTECTED] writes: so a good guess at its definition is that it is obtained from W or one of the others by subtracting the mean and dividing with the SD. With the SD adjusted for ties, of course. (See, e.g., Conover's book.) ...which is actually the exact SD, conditional on the set of tied ranks, not just a correction term. See my discussion with Torsten a month or so ago. yes, exactly. Thanks, Peter! The `T' values reported by functions in the `coin' package are _standardized_ statistics. Standardization is done utilizing the conditional expectation and conditional variance of the underlying linear statistics as given by Strasser Weber (1999). Note that _no_ `continuity correction' whatsoever is applied. The limit distribution is normal (or chisq, when the test statistic is a quadratic form). The vignette explains the theoretical framework `coin' maps into software in more detail. It _definitively_ is worse the effort to have a look at it. At first glance it might seem a little bit abstract but after this you'll see how general and powerful the tools are. We are currently working on a manuscript showing more applications, so watch out for the new `coin' version in a few days. Best, Torsten -- 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 ~~ - ([EMAIL PROTECTED]) FAX: (+45) 35327907 __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
[R] how to put constraint in R?
Dear all, I have a problem when I was working on Age-Period-Cohort study in R. I tried to put constraint to two coefficients on age (so that to solve the identification problem due to linear dependency). But I don't know how to do this in R(put constraint). If you could give me some suggestion, it will be very helpful! Oana __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
Re: [R] glmmADMB: Generalized Linear Mixed Models using AD Model Builder
I get upset when software dies and refuses to give me an answer. I'd much rather have a routine give me a wrong answer -- with an error message -- than just an error message. Maybe refuse to print standard errors when the hessian is singular, but at least give me a progress report with the singular hessian. Without that, I have to program optim or something else separately to get the answers and the hessian in order to do my own diagnosis -- if I know enough to do that. Just my 0.02 Euros. spencer graves Roel de Jong wrote: Of course it is generally possible to generate datasets for a perfectly well-defined model that are hard to fit, but in this particular case I feel it should be possible. In my observations, glmm.admb is far more numerically stable fitting GLMM's than other software I've seen. Further , I don't think the data I generated come from a model that is overparameterized, severely contaminated with outliers, has no noise, or is nonlinear. But I encourage anyone to run a simulation study with generated data they think are acceptable and compare the robustness of several methods. I leave it at this. Best regards, Roel de Jong Berton Gunter wrote: May I interject a comment? When data is generated from a specified model with reasonable parameter values, it should be possible to fit such a model successful, or is this me being stupid? Let me take a turn at being stupid. Why should this be true? That is, why should it be possible to easily fit a model that is generated ( i.e. using a pseudo-random number generator) from a perfectly well-defined model? For example, I can easily generate simple linear models contaminated with outliers that are quite difficult to fit (e.g. via resistant fitting methods). In nonlinear fitting, it is quite easy to generate data from oevrparameterized models that are quite difficult to fit or whose fit is very sensitive to initial conditions. Remember: the design (for the covariates) at which you fit the data must support the parameterization. The most dramatic examples are probably of simple nonlinear model systems with no noise which produce chaotic results when parameters are in certain ranges. These would be totally impossible to recover from the data. So I repeat: just because you can generate data from a simple model, why should it be easy to fit the data and recover the model? Cheers, Bert Gunter Genentech __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html -- Spencer Graves, PhD Senior Development Engineer PDF Solutions, Inc. 333 West San Carlos Street Suite 700 San Jose, CA 95110, USA [EMAIL PROTECTED] www.pdf.com http://www.pdf.com Tel: 408-938-4420 Fax: 408-280-7915 __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
[R] GLMMGibbs
Hello, I am trying to use glmm() in library GLMMGibbs, but I don't seem to have the package and it is not listed on CRAN. Is it no longer supported? (I am using R 2.1.1 on Windows.) Many thanks in advance for your help. Regards, Mark The information contained in this e-mail is confidential and...{{dropped}} __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
Re: [R] Random effects with glm()
On Ti, 2005-12-20, 13:09, Juan Pablo Sánchez skrev: [...] Thus my question is: Do exit same option in the glm() function to allow for random effects?, similar to the random option in lme() No, you can't fit GLMMs with the `glm' function. Instead, take a look at e.g. the `glmmML', `lmer' and `glmmPQL' functions in the glmmML, Matrix and MASS packages respectively. HTH, Henric __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
Re: [R] GLMMGibbs
On Wed, 21 Dec 2005, Edmondson-Jones, Mark wrote: I am trying to use glmm() in library GLMMGibbs, but I don't seem to have the package and it is not listed on CRAN. It _is_ listed in the Devel section (as it has been since 2002). Is it no longer supported? (I am using R 2.1.1 on Windows.) There is a Windows port on my site, as there always has been. R 2.1.1 is obselete, but I would have expected it by default to look there. Set repos=http://www.stats.ox.ac.uk/pub/RWin; if this is not happening for you. -- Brian D. Ripley, [EMAIL PROTECTED] Professor of Applied Statistics, http://www.stats.ox.ac.uk/~ripley/ University of Oxford, Tel: +44 1865 272861 (self) 1 South Parks Road, +44 1865 272866 (PA) Oxford OX1 3TG, UKFax: +44 1865 272595 __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
Re: [R] Help to find only one class and differennt class
Thanks to Jim Holtman. This is very usefull to improve my script. Best, Muhammad Subianto On this day 20/12/2005 17:19, jim holtman wrote: try this: set.seed(1) # generate some test data x.1 - data.frame(seg=sample(1:6,20,T), class=sample(c('good', 'poor'),20,T)) x.1 (x.sp - split(x.1, x.1$seg)) # test each segment for occurance of class. lapply(x.sp, function(.seg){ if (all(.seg$class == 'good')) return('good') if (all(.seg$class == 'poor')) return('poor') return(good poor) }) On 12/20/05, Muhammad Subianto [EMAIL PROTECTED] wrote: Dear R users, I have a problem, which I can not find a solution. Probably someone could help me? I have a result from my classification, like this credit.toy [[1]] age married ownhouse income gender class 1 20-30 no nolow male good 2 40-50 no yes medium female good [[2]] age married ownhouse income gender class 1 20-30 yes yes high male poor 2 20-30 no yes high male good 3 20-30 yes nolow female poor 4 60-70 yes yeslow female poor 5 60-70 no yes high male poor [[3]] age married ownhouse income gender class 1 30-40 yes no high male good 2 20-30 no yes medium female good [[4]] age married ownhouse income gender class 1 50-60 yes yeslow female poor 2 40-50 yes no medium male poor 3 20-30 no no high female poor [[5]] age married ownhouse income gender class 1 40-50 no yeslow female good 2 60-70 no yes medium male poor 3 30-40 yes no high female poor [[6]] age married ownhouse income gender class 1 30-40 no no medium female good 2 50-60 yes yes high female good 3 30-40 yes no high female good credit.toy[[5]]$class [1] good poor poor Levels: good poor How can I count there are only one class and differennt class. I need the result something like good class : 1,3,6 poor class : 4 good and poor class : 2,5 Thanks in advance. Sincerely, Muhammad Subianto __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html -- Jim Holtman Cincinnati, OH +1 513 247 0281 What the problem you are trying to solve? __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
[R] transpose a matrix?
I have a data set in the following format: x-data.frame(id=c(a,b,c),2005-01-15=c(100,225,425), 2005-02-23=c(1100,2325,4525)) x id X2005.01.15 X2005.02.23 1 a 1001100 2 b 2252325 3 c 4254525 I want: id a b c X2005.01.15 100 225 425 X2005.02.23 1100 2325 4525 Any Suggestions? __ [[alternative HTML version deleted]] __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
[R] probs in maps package
Hi all, I am having problems in loading the maps package. Did anyone experienced anything similar? Cheers, Marco [[alternative HTML version deleted]] __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
[R] Why lmer() is not working, altough lme4 is installed?
I have installed lme4 library, but when I try something with lmer() function, I receive error message. On the other hand, I can use lme() function from the same library. Are those two the very same function or not? I am a bit confused. I am using: $platform: i386-pc-linux-gnu $arch: i386 $os: linux-gnu $system: i386, linux-gnu $major: 2 $minor: 0.1 $year: 2004 $month: 11 $day: 15 Sincerely, Petar Milin Assistant Professor Department of Psychology University of Novi Sad Serbia and Montenegro __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
Re: [R] probs in maps package
Giannitrapani, Marco GSUK-GSSC wrote: Hi all, I am having problems in loading the maps package. Did anyone experienced anything similar? Please read the posting guide and tell us why you think you have those problems. At least tell us the error message, which versions of R and maps you are using, and your OS. Uwe Ligges Cheers, Marco [[alternative HTML version deleted]] __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
Re: [R] transpose a matrix?
t c wrote: I have a data set in the following format: x-data.frame(id=c(‘a’,’b’,’c’),’2005-01-15’=c(100,225,425), ’2005-02-23’=c(1100,2325,4525)) x id X2005.01.15 X2005.02.23 1 a 1001100 2 b 2252325 3 c 4254525 I want: id a b c X2005.01.15 100 225 425 X2005.02.23 1100 2325 4525 Any Suggestions? I do not get your point, since subject line and body of your message are telling different stories. Do you want to have a list of vectors? You certainly do not want to transpose a data frame with both factors (or character) and numeric values in it. Uwe Ligges __ [[alternative HTML version deleted]] __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
Re: [R] Why lmer() is not working, altough lme4 is installed?
Petar Milin wrote: I have installed lme4 library, but when I try something with lmer() function, I receive error message. On the other hand, I can use lme() function from the same library. Are those two the very same function or not? I am a bit confused. 1. lme4 is a *package*, not a library 2. a function lme() is not part of recent versions of lme4. You told us you are using an ancient version of R, but nothing about the version of lme4 (which is porbably outdated as well, since new versions won't work on such an ancient version of R, I believe). 3. Why do you conceal the error message of lmer()? Please read the posting guide and send information that is helpful for the helpers to help. Uwe Ligges I am using: $platform: i386-pc-linux-gnu $arch: i386 $os: linux-gnu $system: i386, linux-gnu $major: 2 $minor: 0.1 $year: 2004 $month: 11 $day: 15 Sincerely, Petar Milin Assistant Professor Department of Psychology University of Novi Sad Serbia and Montenegro __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
Re: [R] Why lmer() is not working, altough lme4 is installed?
On On, 2005-12-21, 12:51, Petar Milin skrev: I have installed lme4 library, but when I try something with lmer() function, I receive error message. On the other hand, I can use lme() function from the same library. Are those two the very same function or not? I am a bit confused. At least in recent versions of the lme4 package there's no `lme' function, and in fact there's no fitting functions for (G)LMMs whatsoever. These have been transfered to the Matrix package during the development process -- the function you're looking for is called `lmer'. From below, your R installation is seriously outdated. Matrix need R = 2.2.0, so you must update (which is a good idea, anyway!). HTH, Henric I am using: $platform: i386-pc-linux-gnu $arch: i386 $os: linux-gnu $system: i386, linux-gnu $major: 2 $minor: 0.1 $year: 2004 $month: 11 $day: 15 Sincerely, Petar Milin Assistant Professor Department of Psychology University of Novi Sad Serbia and Montenegro __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html--- __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
Re: [R] transpose a matrix?
-BEGIN PGP SIGNED MESSAGE- Hash: SHA1 Not sure what you want from the explanation you gave but to transpose try that: x - as.matrix(x) x.trans - t(x) One method that's may also of use is help.search(transpose) David On Dec 20, 2005, at 17:26, t c wrote: I have a data set in the following format: x-data.frame(id=c(a,b,c),2005-01-15=c(100,225,425), 2005-02-23=c(1100,2325,4525)) x id X2005.01.15 X2005.02.23 1 a 1001100 2 b 2252325 3 c 4254525 I want: id a b c X2005.01.15 100 225 425 X2005.02.23 1100 2325 4525 Any Suggestions? __ [[alternative HTML version deleted]] __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html -BEGIN PGP SIGNATURE- Version: GnuPG v1.4.1 (Darwin) iD8DBQFDqUsI7EoGVUIQyhERArLdAKCX7FniqohYs646riJopkqs6/rboQCcDBUK 4n9JS+hzHOwLZLc6HKQWJcM= =U6e6 -END PGP SIGNATURE- __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
Re: [R] transpose a matrix?
-BEGIN PGP SIGNED MESSAGE- Hash: SHA1 Not sure what you want from the explanation you gave but to transpose try that: x - as.matrix(x) x.trans - t(x) One method that's may also of use is help.search(transpose) David On Dec 20, 2005, at 17:26, t c wrote: I have a data set in the following format: x-data.frame(id=c(a,b,c),2005-01-15=c(100,225,425), 2005-02-23=c(1100,2325,4525)) x id X2005.01.15 X2005.02.23 1 a 1001100 2 b 2252325 3 c 4254525 I want: id a b c X2005.01.15 100 225 425 X2005.02.23 1100 2325 4525 Any Suggestions? __ [[alternative HTML version deleted]] __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html -BEGIN PGP SIGNATURE- Version: GnuPG v1.4.1 (Darwin) iD8DBQFDqUtZ7EoGVUIQyhERAohmAJ9ASkIETkTvBP7nT8Tr739H7gwWjwCgiBji LpWmylZvZ6al91b02rrAtGg= =a98J -END PGP SIGNATURE- __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
Re: [R] Wilcoxon Mann-Whitney Rank Sum Test in R
Peter, You're right, of course, as usual. Sorry about that. Peter E. Peter Dalgaard wrote: P Ehlers [EMAIL PROTECTED] writes: so a good guess at its definition is that it is obtained from W or one of the others by subtracting the mean and dividing with the SD. With the SD adjusted for ties, of course. (See, e.g., Conover's book.) ...which is actually the exact SD, conditional on the set of tied ranks, not just a correction term. See my discussion with Torsten a month or so ago. __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
Re: [R] Problems installing R 2.1.1. from rpm
May be there is a difference between SuSE and OpenSuSE nowadays?! I exclusively use OpenSuSE now and was under the impression those were equivalent. The main difference between SuSE and OpenSuSE is that SuSE contains some non-GPL software not directly available for OpenSuSE. The most obvious examples are that Adobe Reader, Flash, Java 1.5.x, and RealPlayer come installable by yast on SuSE whereas you need to find them and manually install them for OpenSuSE (yawn). A less obvious example is that a non-GPL soft-modem driver is included in SuSE but not OpenSuSE. Note that the kernel for SuSE is described as 'non-GPL'. [[alternative HTML version deleted]] __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
[R] inconsistent behaviour of ifelse and if ... else
is the behaviour val - ifelse(TRUE, numeric(0), 123) val #NA intended or is it a bug, i.e. should an empty object be returned as might be expected(also in comparsion to what an explicit val - {if(TRUE) numeric(0) else 123} yields)? thanks, joerg __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
Re: [R] inconsistent behaviour of ifelse and if ... else
When in doubt, check the doc first. In this case, ?ifelse says in no fewer than three places why what you described is intended and not a bug. Andy From: Joerg van den Hoff is the behaviour val - ifelse(TRUE, numeric(0), 123) val #NA intended or is it a bug, i.e. should an empty object be returned as might be expected(also in comparsion to what an explicit val - {if(TRUE) numeric(0) else 123} yields)? thanks, joerg __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
[R] Random numbers
Hi All. I have R code whose functionality is being replicated within a C+ program. The outputs are to be compared to validate the conversion somewhat - however (as is always the case) I have stuffed my code with random number calls. Random uniform numbers in C+ are being produced using the (Boost) mersenne-twister generators (mt11213b mt19937) - which is the default type of generator in R (if I read things correctly). If it was all within R I would just set the seed for reproducibility. Basically - how do I specify in C+ for a set of random uniform numbers such that they are the same as from R? I have considered the possibility of storing/using the R generated random numbers in the C+ version for validation purposes - but there are a lot of them, and that strikes me as a generally ugly way of doing things. thanks in advance C -- ~ Carl Donovan Lecturer in statistics Ph +44 1334 461802 The Observatory Buchanan Gardens University of St Andrews St Andrews Fife KY16 9LZ Scotland __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
Re: [R] Random numbers
On 12/21/2005 9:47 AM, Carl wrote: Hi All. I have R code whose functionality is being replicated within a C+ program. The outputs are to be compared to validate the conversion somewhat - however (as is always the case) I have stuffed my code with random number calls. Random uniform numbers in C+ are being produced using the (Boost) mersenne-twister generators (mt11213b mt19937) - which is the default type of generator in R (if I read things correctly). If it was all within R I would just set the seed for reproducibility. Basically - how do I specify in C+ for a set of random uniform numbers such that they are the same as from R? I have considered the possibility of storing/using the R generated random numbers in the C+ version for validation purposes - but there are a lot of them, and that strikes me as a generally ugly way of doing things. I'd say the only reasonable way to do this is to call the R generators rather than trying to duplicate them. R tries hard to keep its generators consistent from version to version, but if you have an independent implementation of the same algorithm, it's going to be very hard to validate that you've really got things exactly identical. The Writing R Extensions manual tells how to call the R generators from other programs. You can do it without going through interpreted R code, so there shouldn't be much in the way of a performance penalty. Duncan Murdoch __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
Re: [R] Random numbers
You can use Marsaglia's multiply with carry. I haven't looked at the C code in R recently, but doubt if it has changed. The C code is very neat, using 6 #defines: static const double RANDCONST=2.32830643654e-10; unsigned long zSeed=362436069, wSeed=521288629; #define zNew ((zSeed=36969*(zSeed65535)+(zSeed16))16) #define wNew ((wSeed=18000*(wSeed65535)+(wSeed16))65535) #define IUNIFORM (zNew+wNew) #define UNIFORM ((zNew+wNew)*RANDCONST) #define setseed(A,B) zSeed=(A);wSeed=(B); #define getseed(A,B) A=zSeed;B=wSeed; See Marsaglia's DIEHARD page for more details: http://www.stat.fsu.edu/pub/diehard/ Carl wrote: Hi All. I have R code whose functionality is being replicated within a C+ program. The outputs are to be compared to validate the conversion somewhat - however (as is always the case) I have stuffed my code with random number calls. Random uniform numbers in C+ are being produced using the (Boost) mersenne-twister generators (mt11213b mt19937) - which is the default type of generator in R (if I read things correctly). If it was all within R I would just set the seed for reproducibility. Basically - how do I specify in C+ for a set of random uniform numbers such that they are the same as from R? I have considered the possibility of storing/using the R generated random numbers in the C+ version for validation purposes - but there are a lot of them, and that strikes me as a generally ugly way of doing things. thanks in advance C -- Bob Wheeler --- http://www.bobwheeler.com/ ECHIP, Inc. --- Randomness comes in bunches. __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
Re: [R] How do I edit the x-axis on a time series plot?
Phil, Does the following do what you want? plot(RecfS, ylab = 'Temperature (deg C)', xlab = 'Year', main = 'Average air temperature (deg C) at Recife, Brazil, in successive months from 1953 to 1962', adj = 0.5, axes=FALSE) axis(1, at=1952:1962, label=paste(Jan, 52:62), las=2) axis(2) box() --Matt -Original Message- From: [EMAIL PROTECTED] [mailto:[EMAIL PROTECTED] Behalf Of Philip Turk Sent: Tuesday, December 20, 2005 8:37 PM To: r-help@stat.math.ethz.ch Subject: [R] How do I edit the x-axis on a time series plot? I am merely trying to reproduce Figure 1.2 of Chris Chatfield's 6th edition of his The Analysis of Time Series: An Introduction (page 2). The S-PLUS code is on pages 305-306. I am almost there but I am having a heck of a time trying to modify and change the x-axis per the book. The book shows the x-axis with 10 tick marks, correctly positioned, and labeled Jan 53, ..., Jan 62. I have not provided the data for the sake of brevity although it is readily available at http://www.bath.ac.uk/~mascc/Recife.TS Can anyone help? recife - as.vector(t(recife)) RecfS - ts(recife, start = c(1953,1), frequency = 12) plot(RecfS, ylab = Temperature (deg C), xlab = Year, main = Average air temperature (deg C) at Recife, Brazil, in successive months from 1953 to 1962, adj = 0.5) Thanks, Philip Turk __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
Re: [R] Newbie - Summarize function
Dear Andrew Could you provide a reproducible example, please? Since we do not have your data test.csv, we can not reproduce your code and that complicates bug fixing a lot. You can use set.seed to create artificial reproducible examples. The only error in your code that I recognized: test.2 - with(test,summarize(test$x,llist(test$Stratum,test$plot),g)) You have a llist(...) instead of list(...) If this is only copy-paste error, then you should provide a reproducible example. If it already solves the problem, you were lucky :-) Regards, Christoph -- Christoph Buser [EMAIL PROTECTED] Seminar fuer Statistik, LEO C13 ETH (Federal Inst. Technology) 8092 Zurich SWITZERLAND phone: x-41-44-632-4673 fax: 632-1228 http://stat.ethz.ch/~buser/ -- [EMAIL PROTECTED] writes: Dear R Users, I have searched through the archives but I am still struggling to find a way to process the below dataset. I have a dataset that has stratum and plot identifier. Within each plot there is variable (Top) stating the number of measurments that should be used to to calculate the mean to the largest top elements within one of the vectors (X). I would like to process this summary statistic by groups. At this stage I have been trying to use the summarize function within the Hmisc library but I am getting the following error Error in eval(expr, envir, enclos) : numeric 'envir' arg not of length one In addition: Warning message: no finite arguments to max; returning -Inf. Any suggetsions on how I can fix this would be greatly appreciated. Kind regards Andrew test - read.table(test.csv, header=TRUE, sep=,) #function to calculate mean of top elements within a plot g-function(y) { + top_no -max(y$top) + weight - with(y,as.numeric(x=x[order(x,decreasing=TRUE)[top_no]])) + wtd.mean(y$x,weight) + } g(test) [1] 172.6667 #call to summarize function - use function g and summarise by stratum plot test.2 - with(test,summarize(test$x,llist(test$Stratum,test$plot),g)) Error in eval(expr, envir, enclos) : numeric 'envir' arg not of length one In addition: Warning message: no finite arguments to max; returning -Inf traceback() 9: eval(substitute(expr), data, enclos = parent.frame()) 8: with.default(y, as.numeric(x = x[order(x, decreasing = TRUE)[top_no]])) 7: with(y, as.numeric(x = x[order(x, decreasing = TRUE)[top_no]])) 6: FUN(X, ...) 5: summarize(test$x, llist(test$Stratum, test$plot), g) 4: eval(expr, envir, enclos) 3: eval(substitute(expr), data, enclos = parent.frame()) 2: with.default(test, summarize(test$x, llist(test$Stratum, test$plot), g)) 1: with(test, summarize(test$x, llist(test$Stratum, test$plot), g)) The version im running on is $platform [1] i386-pc-mingw32 $arch [1] i386 $os [1] mingw32 $system [1] i386, mingw32 $status [1] $major [1] 2 $minor [1] 2.0 $year [1] 2005 $month [1] 10 $day [1] 06 $svn rev [1] 35749 $language [1] R Stratum plot idtop x 1 1 1 2 12 1 1 2 2 41 1 1 3 2 12 1 1 4 2 43 1 1 5 2 12 1 1 6 2 14 1 1 7 2 43 1 1 8 2 12 1 2 1 4 42 1 2 2 4 12 1 2 3 4 432 1 2 4 4 12 1 2 5 4 12 1 2 6 4 14 1 2 7 4 41 1 2 8 4 1 2 1 1 2 12 2 1 2 2 41 2 1 3 2 12 2 1 4 2 43 2 1 5 2 12 2 1 6 2 14 2 1 7 2 43 2 1 8 2 12 2 2 1 3 42 2 2 2 3 12 2 2 3 3 432 2 2 4 3 12 2 2 5 3 12 2 2 6 3 14 2 2 7 3 41 2 2 8 3 1 [[alternative HTML version deleted]] __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
[R] Course *** R/Splus Advanced Programming *** Seattle, January 12th-13th, 2006
__ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
Re: [R] Newbie - Summarize function
Look at ?summarize . The FUN argument is supposed to be a function that inputs a vector but your g inputs a data frame. I think you want something like this (assuming package Hmisc): mApply(test, test[,1:2], g) On 12/20/05, [EMAIL PROTECTED] [EMAIL PROTECTED] wrote: Dear R Users, I have searched through the archives but I am still struggling to find a way to process the below dataset. I have a dataset that has stratum and plot identifier. Within each plot there is variable (Top) stating the number of measurments that should be used to to calculate the mean to the largest top elements within one of the vectors (X). I would like to process this summary statistic by groups. At this stage I have been trying to use the summarize function within the Hmisc library but I am getting the following error Error in eval(expr, envir, enclos) : numeric 'envir' arg not of length one In addition: Warning message: no finite arguments to max; returning -Inf. Any suggetsions on how I can fix this would be greatly appreciated. Kind regards Andrew test - read.table(test.csv, header=TRUE, sep=,) #function to calculate mean of top elements within a plot g-function(y) { + top_no -max(y$top) + weight - with(y,as.numeric(x=x[order(x,decreasing=TRUE)[top_no]])) + wtd.mean(y$x,weight) + } g(test) [1] 172.6667 #call to summarize function - use function g and summarise by stratum plot test.2 - with(test,summarize(test$x,llist(test$Stratum,test$plot),g)) Error in eval(expr, envir, enclos) : numeric 'envir' arg not of length one In addition: Warning message: no finite arguments to max; returning -Inf traceback() 9: eval(substitute(expr), data, enclos = parent.frame()) 8: with.default(y, as.numeric(x = x[order(x, decreasing = TRUE)[top_no]])) 7: with(y, as.numeric(x = x[order(x, decreasing = TRUE)[top_no]])) 6: FUN(X, ...) 5: summarize(test$x, llist(test$Stratum, test$plot), g) 4: eval(expr, envir, enclos) 3: eval(substitute(expr), data, enclos = parent.frame()) 2: with.default(test, summarize(test$x, llist(test$Stratum, test$plot), g)) 1: with(test, summarize(test$x, llist(test$Stratum, test$plot), g)) The version im running on is $platform [1] i386-pc-mingw32 $arch [1] i386 $os [1] mingw32 $system [1] i386, mingw32 $status [1] $major [1] 2 $minor [1] 2.0 $year [1] 2005 $month [1] 10 $day [1] 06 $svn rev [1] 35749 $language [1] R Stratum plot idtop x 1 1 1 2 12 1 1 2 2 41 1 1 3 2 12 1 1 4 2 43 1 1 5 2 12 1 1 6 2 14 1 1 7 2 43 1 1 8 2 12 1 2 1 4 42 1 2 2 4 12 1 2 3 4 432 1 2 4 4 12 1 2 5 4 12 1 2 6 4 14 1 2 7 4 41 1 2 8 4 1 2 1 1 2 12 2 1 2 2 41 2 1 3 2 12 2 1 4 2 43 2 1 5 2 12 2 1 6 2 14 2 1 7 2 43 2 1 8 2 12 2 2 1 3 42 2 2 2 3 12 2 2 3 3 432 2 2 4 3 12 2 2 5 3 12 2 2 6 3 14 2 2 7 3 41 2 2 8 3 1 [[alternative HTML version deleted]] __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
Re: [R] bivariate kernel density estimates at point locations (rather than at grid locations)
Hello Dr. Adelchi Azzalini, Thank you for your quick response to my question that I posted on the r-help board about bivariate kernel density estimates. I have been using your sm package the past few days and have encountered a problem with estimating the density for only 1 point. I am using R 2.2.0, sm version 2.1-0 on a Windows machine. Example code below: #The code below creates 3 point locations x.locs = c(74, 75, 77) y.locs = c(64, 63, 61) points = cbind(x.locs, y.locs) #If I send this data into sm.density everything works fine. dens = sm.density(points, h=c(1, 1)) #However, if I only wish to send 1 point location to sm.density, i.e., points.2 =points[1,] dens.2 = sm.density(points.2, h=c(1, 1)) R returns to me the error:length(h) != 1 It appears to me that sm.density thinks that my 1 point is a 1-dimensional location rather than a 2-dimensional location, and I am getting an error when I request a bivariate kernel. Do you have any suggestions? Best, Matt -Original Message- From: Adelchi Azzalini [mailto:[EMAIL PROTECTED] Sent: Friday, December 16, 2005 2:42 AM To: Strickland, Matthew Cc: r-help@stat.math.ethz.ch; [EMAIL PROTECTED] Subject: Re: [R] bivariate kernel density estimates at point locations (rather than at grid locations) On Thu, 15 Dec 2005 14:21:17 -0500, Strickland, Matthew wrote: SM Hi, SM SM My data consists of a set of point locations (x,y). SM SM I would like to know if there is a procedure for bivariate kernel SM density estimation in R that returns the density estimates at the SM observed point locations rather than at grid locations. I have SM looked at a number of different routines and they all seem to return SM estimates at grid locations. SM One option is to use (from package sm), sm.density(xy, eval.points=xy, eval.grid=FALSE) where xy in a (n\times 2) matrix. Best wishes, Adelchi Azzalini -- Adelchi Azzalini [EMAIL PROTECTED] Dipart.Scienze Statistiche, Università di Padova, Italia tel. +39 049 8274147, http://azzalini.stat.unipd.it/ __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
[R] System Reliability Metrics
I need to calculate some metrics such as Mean Time Between Failure (MTBF), etc (see http://www.cs.sandia.gov/~jrstear/ras for a more complete list). I have observations like start endstate 1 2005-11-11 09:05:00 2005-11-11 12:20:00 Scheduled Downtime 2 2005-11-12 13:42:00 2005-11-12 14:45:00 Unscheduled Downtime where each row describes the system state between start and end times. Time between observations indicates a Production state. The metrics of interest involve simple ratios of total time spent in various states, number of transitions, etc. I'd like to plot period MTBF values (eg monthly vertical bars), as well as a cumulative MTBF (eg a line whose last value indicates MTBF for the entire time range), etc. What is the best approach in R towards these results? Irregular time series seem a natural fit for the observations, and the reporting periods for the metrics will have regular periods - so I've perused the stats, tseries, and its packages. A markov class could be used (eg msm package), but that's probably overkill (like the reliability packages concord and irr)? My goal is to calculate the metrics in the simplest and most natural way. Can someone please advise me on a best approach? Thank you! -- +--+ | Jon Stearley (505) 845-7571 (FAX 844-9297) | | Sandia National Laboratories Scalable Systems Integration | +--+ __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
Re: [R] Newbie - Summarize function
Just one follow up to my previous reply. To use summarize with this problem try this: summarize(rownames(test), test[,1:2], function(r) g(test[r,])) This define a funtion which inputs a vector of row names and outputs g acting on the data.frame consisting of those rows only. On 12/21/05, Gabor Grothendieck [EMAIL PROTECTED] wrote: Look at ?summarize . The FUN argument is supposed to be a function that inputs a vector but your g inputs a data frame. I think you want something like this (assuming package Hmisc): mApply(test, test[,1:2], g) On 12/20/05, [EMAIL PROTECTED] [EMAIL PROTECTED] wrote: Dear R Users, I have searched through the archives but I am still struggling to find a way to process the below dataset. I have a dataset that has stratum and plot identifier. Within each plot there is variable (Top) stating the number of measurments that should be used to to calculate the mean to the largest top elements within one of the vectors (X). I would like to process this summary statistic by groups. At this stage I have been trying to use the summarize function within the Hmisc library but I am getting the following error Error in eval(expr, envir, enclos) : numeric 'envir' arg not of length one In addition: Warning message: no finite arguments to max; returning -Inf. Any suggetsions on how I can fix this would be greatly appreciated. Kind regards Andrew test - read.table(test.csv, header=TRUE, sep=,) #function to calculate mean of top elements within a plot g-function(y) { + top_no -max(y$top) + weight - with(y,as.numeric(x=x[order(x,decreasing=TRUE)[top_no]])) + wtd.mean(y$x,weight) + } g(test) [1] 172.6667 #call to summarize function - use function g and summarise by stratum plot test.2 - with(test,summarize(test$x,llist(test$Stratum,test$plot),g)) Error in eval(expr, envir, enclos) : numeric 'envir' arg not of length one In addition: Warning message: no finite arguments to max; returning -Inf traceback() 9: eval(substitute(expr), data, enclos = parent.frame()) 8: with.default(y, as.numeric(x = x[order(x, decreasing = TRUE)[top_no]])) 7: with(y, as.numeric(x = x[order(x, decreasing = TRUE)[top_no]])) 6: FUN(X, ...) 5: summarize(test$x, llist(test$Stratum, test$plot), g) 4: eval(expr, envir, enclos) 3: eval(substitute(expr), data, enclos = parent.frame()) 2: with.default(test, summarize(test$x, llist(test$Stratum, test$plot), g)) 1: with(test, summarize(test$x, llist(test$Stratum, test$plot), g)) The version im running on is $platform [1] i386-pc-mingw32 $arch [1] i386 $os [1] mingw32 $system [1] i386, mingw32 $status [1] $major [1] 2 $minor [1] 2.0 $year [1] 2005 $month [1] 10 $day [1] 06 $svn rev [1] 35749 $language [1] R Stratum plot idtop x 1 1 1 2 12 1 1 2 2 41 1 1 3 2 12 1 1 4 2 43 1 1 5 2 12 1 1 6 2 14 1 1 7 2 43 1 1 8 2 12 1 2 1 4 42 1 2 2 4 12 1 2 3 4 432 1 2 4 4 12 1 2 5 4 12 1 2 6 4 14 1 2 7 4 41 1 2 8 4 1 2 1 1 2 12 2 1 2 2 41 2 1 3 2 12 2 1 4 2 43 2 1 5 2 12 2 1 6 2 14 2 1 7 2 43 2 1 8 2 12 2 2 1 3 42 2 2 2 3 12 2 2 3 3 432 2 2 4 3 12 2 2 5 3 12 2 2 6 3 14 2 2 7 3 41 2 2 8 3 1 [[alternative HTML version deleted]] __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
[R] linking C and R
hey, I am running R 2.0.1 on a the terminal of my MAC OS X and I have written some C code that I would like to use dynload to bring into R. When I try to compile the code i get the error R.defines.h no such file or directory. I know that the file is in resources/include but where do I have to move the file to so that the compiler can access it? I tried copying Rdefines.h and R_ext folders into the folder where the code is and using #include Rdefines.h instead of #include Rdefines.h. I now get a different error R_ext/Memory.h: no such file or directory even though r_ext is in the folder. Any suggestions? Thanks, Elizabeth Lawson __ [[alternative HTML version deleted]] __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
Re: [R] linking C and R
I don't know much about Macs, but are you using R CMD SHLIB whatever.c to compile the code? If you simply invoke the compiler by hand, I'd expect you run into problems like that. Andy From: Elizabeth Lawson hey, I am running R 2.0.1 on a the terminal of my MAC OS X and I have written some C code that I would like to use dynload to bring into R. When I try to compile the code i get the error R.defines.h no such file or directory. I know that the file is in resources/include but where do I have to move the file to so that the compiler can access it? I tried copying Rdefines.h and R_ext folders into the folder where the code is and using #include Rdefines.h instead of #include Rdefines.h. I now get a different error R_ext/Memory.h: no such file or directory even though r_ext is in the folder. Any suggestions? Thanks, Elizabeth Lawson __ [[alternative HTML version deleted]] __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
[R] Help with Krige.conv using linear models
A majority of my data makes a kriged map perfectly using an exponential model for the semivariogram to fit my data and then going through the commands variofit() to define the model and then krige.conv() to use the model to predict values in a grid. But…one set of my data appears to be linearly correlated for the first 5000 meters and not correlated beyond that. I have been having problems using krige.conv() to get a decent kriged map using the linear model. The code I am using from my data is as follows: modeltest=variofit(variotest, weights=’cressie’, cov.model=’linear’, ini.cov.pars=c(80,1)) The output parameters are tausq = 9.855, sigmasq = 0.0087, phi=1.0 krig=krige.conv(data, krige=krige.control(type.krig=’ok’, obj.model=modeltest), locations=pred.grid) At this point, krig$predict values have little to no variability (1.897 +/- 0.004), where I would expect values between 0 – 15. By running the same data, except using an exponential model such as: modeltest=variofit(variotest, weights=’cressie’, cov.model=’exponential’) This model appears to fit the data (only the first 5 km) about the same as the linear model except now the output parameters are tausq=10.02, sigmasq=318909, and phi = 3714567. And calling krige.conv() again, the predicted values are in the range that I would expect, and the kriged map looks fine. I’m not sure if this has something to do with how the kriging is using the model beyond the 5 km. It seems like I need to be able to set the function to only apply the linear weighting to the linearly correlated portion (data less than 5km away), and the rest to 0, but I’m not sure how to do that (or maybe I’m completely going down the wrong track). I’m using Windows XP pro OS with R 2.1.1. Please help the neophyte statistician. To figure this out is the only Christmas gift that I need. Thanks. __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
Re: [R] boot problem
Your 'resample' function is not written according to the help page. Try resample - function(x, index) { x[index, ] } -roger david v wrote: Hello, This is the code that is giving me problems library(boot) data-read.table(test,header=FALSE,sep=\t,row.names=1) data V2 V3 V4 A 5 8 9 B 12 54 89 C 65 89 23 D 32 69 44 E 21 84 97 F 33 59 71 G 16 45 93 H2 46 55 I 22 33 88 resample - function(x,index) { sample(data,replace=TRUE) } dist-boot(data,resample,R=1000) Erreur : nombre d'indices incorrect sur la matrice (french) Error: number of indices wrong in the matrix (moreless) Can anybody help??? __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html -- Roger D. Peng | http://www.biostat.jhsph.edu/~rpeng/ __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
[R] Huber location estimate
We have a choice when calculating the Huber location estimate: set.seed(221205) y - 7 + 3*rt(30,1) library(MASS) huber(y)$mu [1] 5.9117 coefficients(rlm(y~1)) (Intercept) 5.9204 I was surprised to get two different results. The function huber() works directly with the definition whereas rlm() uses iteratively reweighted least squares. My surprise is because I vaguely remember @ARTICLE{hw77, author = {Holland, P. W. and Welsch, R. E.}, title = {Robust Regression using Iteratively Reweighted Least-Squares}, journal = {Communications in Statistics: Theory and Methods}, volume = {A6(9)}, number = {}, pages = {813-827}, year= {1977} } as saying that the two methods were equivalent. Obviously they aren't quite. Comments welcome. Murray Jorgensen -- Dr Murray Jorgensen http://www.stats.waikato.ac.nz/Staff/maj.html Department of Statistics, University of Waikato, Hamilton, New Zealand Email: [EMAIL PROTECTED]Fax 7 838 4155 Phone +64 7 838 4773 wkHome +64 7 825 0441Mobile 021 1395 862 __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
[R] Logistic regression to select genes and estimate cutoff point?
Hi, all, I am new to R or even to statistics. Not sure if the question has a answer. But I couldn't find a straight forward answer in the help mailing list. I need use MicroArray data to select several diagnostic genes between Normal samples and Tumor samples and use these genes to predict unknow samples. Since the sample size is so small and data doesn't follow normal distribution, I am thinking to use logistic regression instead of Student T test to select genes. To make the problem simpler, I assume each gene is independent to each other without interactions. My questions is how I should build up the model: one model for each gene or a multiple variable model to include all genes? Which is the test to compare the discrimination power of each gene? I am thinking it is Wald statistic for the multiple variable model and Maximum likelihood for the single gene models? Am I correct? To estimate the cutoff point, I guess the answer is the gene expression when p=0.5 in the model. Am I on the right direction? Any suggestion is appreciated! Thanks a lot. Lingsheng [[alternative HTML version deleted]] __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html