similar to: Off topic: SS formulae for 3-way repeated measure anova (for when aov() fails)

I'm looking to analyze a large data set: a within-Ss 2*2*1500 design with 20 Ss. However, aov() gives me an error, reproducible as follows: id = factor(1:20) a = factor(1:2) b = factor(1:2) d = factor(1:1500) temp = expand.grid(id=id, a=a, b=b, d=d) temp$y = rnorm(length(temp[, 1])) #generate some random DV data this_aov = aov( y~a*b*d+Error(id/(a*b*d)) , data=temp ) While yields the

Dear R-help, I'm facing a problem with defining a repeated measures anova with weighted data. Here's the code to reproduce the problem: # generate some data seed=11 rtrep <- data.frame(rt=rnorm(100),ti=rep(1:5,20),subj=gl (20,5,100),we=runif(100)) # model with within factor for subjects/repeated measurements, no problem aov(rt~ti + Error(subj/ti),data=rtrep) #model with weights

Hi all, I wonder if you could help me with (what is surely) a simple R question? I've written a simple R script (attached) to perform multiple ANOVAs on the columns in a table loaded in from a a file (also attached). I loop through the list of columns for which I want to perform the ANOVAs, storing the column name in a variable. When I try to perform the ANOVA using the variable name as a

Hi there, some statistical programs (e.g. SPSS) calculate a correction of the degrees of freedom in a repeated measure analysis of variance (see Greenhouse-Geisser (1958) or Huynh-Feld (1976)) by a factor epsilon. This factor is used to correct the deg. of freedom to get a corrected f-test. Is this also possible with R? Thanks, Sven P.S.: I read in the lm help page: singular.ok logical,

Hi all, I am getting the following error message: > mymodel = glm(response ~ . , family=binomial, data=C); Error: cannot allocate vector of size 734.2 Mb In addition: Warning messages: 1: In array(0, c(n, n), list(levs, levs)) : Reached total allocation of 1535Mb: see help(memory.size) 2: In array(0, c(n, n), list(levs, levs)) : Reached total allocation of 1535Mb: see help(memory.size) 3:

Dear List, creating factors in a given non-default orders is notoriously difficult to explain in a course. Students love the ifelse construct given below most, but I remember some comment from Martin M?chler (?) that ifelse should be banned from courses. Any better idea? Not necessarily short, easy to remember is important. Dieter data = c(1,7,10,50,70) levs =

Lattice experts: Can you think of a way to produce a levelplot as below and then add a histogram of the z variable to the top margin of the plot that would sit on top of the color key? x <- seq(pi/4, 5 * pi, length.out = 100) y <- seq(pi/4, 5 * pi, length.out = 100) r <- as.vector(sqrt(outer(x^2, y^2, "+"))) grid <- expand.grid(x=x, y=y) grid$z <- cos(r^2) *

I am new to using S4 methods and have run into this problem (on Windows XP using R 2.4.1): I am writing a package in which I use the graph package. I define my own classes of graphs as: setOldClass("graphsh") setOldClass("ugsh") setIs("ugsh", "graphsh") (I know that I "should have" used setClass instead - and I will eventually - but right now

A number of users have spotted a terminal problem with the 'debug' package under R2.4.0, along the lines of > mtrace(x) > x() Error in attr(value, "row.names") <- rlabs : row names must be 'character' or 'integer', not 'double' This arose from a bug in 'rbind.data.frame' in R2.4.0 itself. The bug is fixed in R2.4.0 patched, so the

I sent this to the list last week, and haven't seen it pop up. Either I deleted it when it did appear, or possibly it was destroyed as spam...? If it did appear and I somehow missed it, appologies. In a nutshell, can the function FUN supplied to by() deduce what level of factor by() was on when FUN was called? I've been digging through the functions, and can't see where the

When attempting to merge 3 data frames, one of which has fewer columns than the others, rbind.data.frame correctly refuses to perform the bind. However, the error message given is a bit obscure due to a logical bug in the match.names() internal function to rbind.data.frame. Illustration: ## Three data frames with same column variable names: > foo <- data.frame(v1 = c('a',

Given the example: R> (levs <- quantile(volcano,c(0,0.1,0.5,0.9,0.99,1))) 0% 10% 50% 90% 99% 100% 94 100 124 170 189 195 R> levelplot(volcano,at=levs) How can I make the key categorical with the size of the divisions equally spaced in the key? E.g., five equal size rectangles with labels at levs c(100,124,170,189,195)? Apologies if this is obvious. -A R> version

>From commits to R devel, I saw attempts to speed up subsetting and 'match', and to cache results of conversion of small nonnegative integers to character string. That's good. I am sorry for pushing, still. Is the partial new behavior of function 'factor' with respect to NA really worthy? match(xlevs, nlevs)[f] looks nice, too. - Using f <- match(xlevs, nlevs)[f]

>>>>> Suharto Anggono Suharto Anggono via R-devel <r-devel at r-project.org> >>>>> on Sun, 15 Oct 2017 16:03:48 +0000 writes: > In R devel, function 'factor' has been changed, allowing and merging duplicated 'labels'. Indeed. That had been asked for and discussed a bit on this list from June 14 to June 23, starting at

For ordered factor the natural contrast coding would be to parametrize by the succsessive differences between levels, which does not assume equal spacing of factor levels as does the polynomial contrasts (implicitly at least). This requires the contr.cum, which could be: contr.cum <- function (n, contrasts = TRUE) { if (is.numeric(n) && length(n) == 1) levs <- 1:n

Dear R-devel list members, I'd like to suggest a more flexible procedure for generating contrast names. I apologise for a relatively long message -- I want my proposal to be clear. I've never liked the current approach. For example, the names generated by contr.treatment paste factor to level names with no separation between the two; contr.sum simply numbers contrasts (I recall an

My idea (like in https://bugs.r-project.org/bugzilla/attachment.cgi?id=1540 ): - For remapping, use f <- match(xlevs, nlevs)[f] instead of f <- match(xlevs[f], nlevs) (I have mentioned it). - Remap only if length(nlevs) differs from length(xlevs) . On use of 'order' in function 'factor' in R devel, factor.Rd still says 'sort.list' in "Details" section. My

I am trying once again. By just changing f <- match(xlevs[f], nlevs) to f <- match(xlevs, nlevs)[f] , function 'factor' in R devel could be made more consistent and back-compatible. Why not picking it? -------------------------------------------- On Sat, 25/11/17, Suharto Anggono Suharto Anggono <suharto_anggono at yahoo.com> wrote: Subject: Re: [Rd] Function

In R devel, function 'factor' has been changed, allowing and merging duplicated 'labels'. Issue 1: Handling of specified 'labels' without duplicates is slower than before. Example: x <- rep(1:26, 40000) system.time(factor(x, levels=1:26, labels=letters)) Function 'factor' is already rather slow because of conversion to character. Please don't add slowdown.

Dear listers, I have a piece of code which performs an ANOVA type of analysis on 2D GC data. The code is shown below: # ANOVA 2D GC analysis # maxc <- number of samples # nreps <- number of samples maxc <- 2 nreps <- 4 sscl <- NULL cmean <- NULL # # Initial stat. variable # dftot <- nrow(mat)-1 dfcl <- maxc - 1 dferr <- dftot - dfcl totmean