[R] expand.grip for permutations
if i were to have a block size of 4 people and i want to assign a treatment combination to the entire block, there would be 16 different treatment combinations (, TTTP, TTPP, PTTP, etc.) i am trying to get all 16 permutations and i am able to use this code below. drugs=c('P','T'); comb=expand.grid(drugs,drugs,drugs,drugs) for a block size of 3 the code would be comb=expand.grid(drugs,drugs,drugs) and for a block size of 2 it would be comb=expand.grid(drugs,drugs). my question is whether there is a way to automatically create the comb variable. i tried using expand.grid(rep(drugs, block.size) but that didn't work. any help on how i can proceed? thanks -- View this message in context: http://r.789695.n4.nabble.com/expand-grip-for-permutations-tp4648067.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] expand.grip for permutations
thank you both! that worked! -- View this message in context: http://r.789695.n4.nabble.com/expand-grip-for-permutations-tp4648067p4648076.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] How make a x,y dataset from a formula based entry
Hello all, So I am using the (formula entry) method for randomForests: randomForest(y~x1+x2+...+x39+x40,data=xxx,...) but the issue is that some of the items in that package dont take a formula entry - you have to explicitly state the y and x vector: randomForest(x=xxx[,c('x1','x2',...,'x40')],y=xxx[,'y'],...) Now my question is whether there is a function/way to tell R to take a formula and make the two corresponding datasets [x,y] (that way I dont have to create the x dataset manually with all 40 variables I have). There must be a more elegant way to do this than x=xxx[,c('x1','x2',...,'x40')] Thanks! George -- View this message in context: http://r.789695.n4.nabble.com/How-make-a-x-y-dataset-from-a-formula-based-entry-tp3834477p3834477.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] Question about plot.mona {cluster}
Hello all, I what to print the banner plot that is output from the mona method in the cluster package but the problem is I dont want to print all that red ink. Here is an example: data(animals) ma - mona(animals) ma ## Plot similar to Figure 10 in Struyf et al (1996) plot(ma) I can change the bar color by using the argument col=c(0,0) - plot(ma,col=c(0,0)) - but then the variable labels also get colored white. Is there a way to remove the bar colors but leave the variables colored? Thank you George Skountrianos -- View this message in context: http://r.789695.n4.nabble.com/Question-about-plot-mona-cluster-tp3802672p3802672.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] How to check conditional dependence
Hello all- Lets say I have my dependent variable Y_ij and a time varying covariate X_ij. I want to formulate some regression model to check if X_ij is dependent on X_i1,X_i2,,X_i(j-1) and Y_i1,Y_i2,,Y_i(j-1). I want to test no dependence on the Y component. I'm thinking a simple linear regression of X_i2,...,X_ij on X_i1,...,X_i(j-1) and Y_i1,...,Y_i(j-1) with NO intercept term using the lm() function should do it. Then I can look at the regression coefficient of Y to test for no dependence on Y. Does this make sense or is there a better/correct way to do this? Thanks George -- View this message in context: http://r.789695.n4.nabble.com/How-to-check-conditional-dependence-tp2545533p2545533.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] Pesky homemade function code
Hi all- this seems to be simple to figure out but since im new to writing functions I dont know what is happening. Here is my code along with the error I am receiving: semivario=function(data,ids,times,resids){ id=unique(data$ids) index=combinations(length(data$times[data$ids==id[1]]),2) time=gamma=numeric(dim(index)[1]) for (j in 1:dim(index)[1]){ time[j]=abs(data$times[data$ids==id[1]][index[j,1]]-data$times[data$ids==id[1]][index[j,2]]) gamma[j]=.5*(data$resids[data$ids==id[1]][index[j,1]]-data$resids[data$ids==id[1]][index[j,2]])^2 } for (i in id[-1]){ index=combinations(length(data$times[data$ids==i]),2) time1=gamma1=numeric(dim(index)[1]) for (j in 1:dim(index)[1]){ time1[j]=abs(data$times[data$ids==i][index[j,1]]-data$times[data$ids==i][index[j,2]]) gamma1[j]=.5*(data$resids[data$ids==i][index[j,1]]-data$resids[data$ids==i][index[j,2]])^2 } time=c(time,time1) gamma=c(gamma,gamma1) } value=list(time=time,gamma=gamma) return(value) } and I would run it as semivario(data=hope,ids=id,times=sctime,resids=scResid) What I want to do is everywhere we see the words data,ids,times,resids to be replaced with, for example, hope,id,sctime,scResid. Think of macros in SAS where we use the before every macro input variable name. Im not sure if this is how R handles function inputs. Here is my error: Error in combinations(length(data$times[data$ids == id[1]]), 2) : bad value of n Thanks -- View this message in context: http://r.789695.n4.nabble.com/Pesky-homemade-function-code-tp2541597p2541597.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] Pesky homemade function code
@Thierry- I am writing my own semivariogram code since I could not find a pre-made function that did what I need it do. The code in the function correctly works but I not sure how to get the function itself to work. In other words if I fill in the commands (hope,id,sctime,scResid) by hand then everything is ok -- but I dont want to do that. Plus this will help be better understand how to program functions in R. -- View this message in context: http://r.789695.n4.nabble.com/Pesky-homemade-function-code-tp2541597p2541696.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] SAS to R
Hi everyone I dont know how to code in SAS but I do know how to code in R. Can someone please be kind enough to translate this into R code for me: proc mixed data = small method = reml; class id day; model weight = day/ solution ddfm = bw; repeated day/ subject=id type = unstructured; run; === so far i think it is gls(weight~day,corr=corSymm(???),method=REML,data=small) my main problem is I dont know how to get the unstructured covariance matrix to work Thank you -- View this message in context: http://r.789695.n4.nabble.com/SAS-to-R-tp2286695p2286695.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] modify the make.link function GLM
can someone please tell me how modify the make.link function i want to update the function with this code but every time i save it R never keeps my new version. i have tried to unbind first and then assign. i also tried the fixInNamespace but that doesnt work either. can someone please tell me how i can append this to the make.link file for good? thank you }, loglog = { linkfun - function(mu) -log(-log(mu)) linkinv - function(eta) exp(-exp(-eta)) mu.eta - function(eta) exp(-exp(-eta)-eta) valideta - function(eta) all(eta != 0) }, stop(sQuote(link), link not recognised)) structure(list(linkfun = linkfun, linkinv = linkinv, mu.eta = mu.eta, valideta = valideta, name = link), class = link-glm) } -- View this message in context: http://r.789695.n4.nabble.com/modify-the-make-link-function-GLM-tp2135906p2135906.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] glm binomial loglog (NOT cloglog) link
can you please say specifically how to modify the make.link function -- View this message in context: http://r.789695.n4.nabble.com/glm-binomial-loglog-NOT-cloglog-link-tp849370p2135909.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.