similar to: Using 'by()' in a function

Hello everyone, I would like to perform a 2-way manova test, but I'm having some issues. I implemented like this Y<-cbind(Resp1,Resp2,Resp3,....,Respn) model<-manova(Y "tilda" FactorA*FactorB) summary.aov(model) 1. I don't know at what level I have to do the Type I error correction. Is it on p-values returned by "summary.aov(model)? Or is it when I compare each

Dear MCMCglmm users, I am currently struggling with the specification of a proper prior and model formula for a multi-response MCMCglmm with two of the three response variables being Gaussian and the third being za-poisson. The model includes several fixed effects and three nested random effects. In general, I would prefer to fit a model with a fixed effect of trait and suppressed intercept for

Hi Is there any way to fit a bivaraite longitudinal mixed model using R. I have a data set with col names resp1 (Y_ij1), resp2 (Y_ij2), timepts (t_ij), unit(i) j=1,2,..,m and i=1,2,..n. I want to fit the following two models Model 1 Y_ij1, Y_ij2 | U_i = u_i ~ N(alpha + u_i + beta1*t_ij, Sigma) U_i ~ iid N(0, sigu^2) Sigma = bivariate AR structure alpha and beta are vectors of order 2.

Hi! I fairly new to R, have only done pretty basic things so far, so this may be a very basic question..... But I did search the forums and didn't see a solution.... I'm trying to get going with kripp.alpha(). I'm loading data from a file, like this: > library(irr) Loading required package: lpSolve > x <- read.table("foo", comment.char="#", header=TRUE,

I am in the process of transferring from an old version of S+ to using R having used a variety of other packages in the past. I'm hugely impressed with R but it has an excellent but depressing habit of exposing that I'm not a professional statistician and has done so again. Someone has run a nice little repeated measures design on my advice, students randomised to four orders of a

Hi all, I'm new to PCA in R, so this might be a basical thing, but I cannot find anything on the net about it. I need to make a PCA plot with two response variables (df$resp1 and df$resp2) against eight metabolites (df$met1, df$met2, ...) and I don't have a clue how to do... and I've only used the simplest PCAs before, like this: pcaObj=prcomp(t(df[idx, c(40:47)]))

Hi, I am bring SPEEX up on Analog Device's Blackfin (using Visual DSP++ tool set). The floating point was too slow on this fixed-point processor so I am going for the integer version. The floating point library build was very clean, but when I build with FIXED_POINT defined, the compiler exits when it find this discrepancy in \libspeex\cb_search.c : ".\libspeex\cb_search.c",

Dear R Users, I am trying to write a wrapper around summarize and xYplot from Hmisc and am having trouble understanding how to pass arguments from the function I am writing to the nested functions. There must be a way, but I have not been able to figure it out. An example is below. Any advice would be greatly appreciated. Thanks, Dan # some example data df=expand.grid(rep=1:4,

Hello, I?m with a problem in using nonlinear quantile regression, the function nlrq. I want to do a quantile regression o nonlinear function in the form a*log(x)-b, the coefficients ?a? and ?b? is my objective. I try to use the command: funx <- function(x,a,b){ res <- a*log(x)-b res } Dat.nlrq <- nlrq(y ~ funx(x, a, b), data=Dat, tau=0.25, trace=TRUE) But a can?t solve de problem,

I Dears, if that wouldn't take u too much effort I'd like to ask for a swift opinion: I have a alinear (mixed effect) model that I wish to run as a piecewise one. When I predict the values Iget quite some odds and disturbing results: The predicted stright line after the break point is not straight at all, instead behaves like if it was a hig order polynomial or something similar!!!! I

Hi. Thank you very much in advance for your help. I have generated data from two simple linear models and used k-means clustering (stats4) to identify two clusters in the generated data. Next, I would like to do simple linear regression for each separate cluster. I can do this if I first use the cluster labels to define two separate data frames with the subset function. However, I would

by() fails for 1-column matrices and dataframes: X <- data.frame(a=1:10) g <- gl(2,5) by(X, g, colMeans) Suggested fix: --- by-old.R 2007-12-10 15:26:22.501086600 +0100 +++ by.R 2007-12-10 15:25:58.390477200 +0100 @@ -26,7 +26,7 @@ IND[[1]] <- INDICES names(IND) <- deparse(substitute(INDICES))[1] } else IND <- INDICES - FUNx <-

Dear all, Recently I've wanted to add support for threads to LLVM (motivated by OpenMP, more or less), but before jumping in and implementing anything, I thought it might be a good idea to describe what I have in mind and ask for comments. Hence this email - if anyone has any comments, I'd be very glad to hear them. WHAT I'M PROPOSING: The addition of two instructions - fork

I have a fix to by.data.frame() that works for my example. Can anyone see a problem with this? The old code has: > get("by.data.frame",3) function (data, INDICES, FUN, ...) { ### code skipped to save space ans <- eval(substitute(tapply(1:nrow(data), IND, FUNx)), ### The problem seems to be here data) attr(ans, "call") <- match.call() class(ans)

Hi, I noticed that by() returns an object of class 'by', regardless of what its argument 'simplify' is. ?by says that it always returns a list if simplify=FALSE, yet by.data.frame shows: ---<--------------------cut here---------------start------------------->--- function (data, INDICES, FUN, ..., simplify = TRUE) { if (!is.list(INDICES)) { IND <-

summary: The function 'by' inconsistently strips class from the data to which it is applied. quick reason: tapply strips class when simplify is set to TRUE (the default) due to the class stripping behaviour of unlist. quick answer: This can be fixed by invoking tapply with simplify=FALSE, or changing tapply to use do.call(c instead of unlist executable example:

I need to remove certain interactions and keep only the one between the second level of the factor and the continuous var t2 bin4 <- glm(resp2~ t*t2+c5.vrm,data=dfa,family="quasibinomial") > summary(bin4) Call: glm(formula = resp2 ~ t * t2 + c5.vrm, family = "quasibinomial", data = dfa) Deviance Residuals: Min 1Q Median 3Q Max -6.5464

Hallo R-users, I'm a R (release 0.65) novice, but have read some about S. Is there a similar function in R like the S function "by()" ? This function groups data typically from a matrix by a variable and applies a function on the grouped data. Example in S: > by(data, year, summary) where "data" is a matrix containing the variable "year". After grouping

I have a question about running an optimization function on an existing LOESS function defined in R. I have a very large dataset (1 million observations) and have run a LOESS regression. Now, I want to run a Newton-Raphson optimization to determine the point at which the slope change is the greatest. I am relatively new to R and have tried several permutations of the maxNR and nlm functions with

When I run Rcmd check on a package on my Windows 2000 machine, I get a series of error messages like the following: * checking generic/method consistency ...c:\DOCUME~1\R5018~1.WOO\LOCALS~1\Temp/R utils138414013: cannot open c:DOCUME~1R5018~1.WOOLOCALS~1Temp/Rin138408157: no s uch file It looks as if a Windows style path to the temp directory is not being interpreted correctly, with backslashes