similar to: bug in cor (..., use= ...)?

Dear R users, Is there something like predict (..., type= 'response') for glmmPQL objects or how would I get fitted values on the scale of the response variable for the binomial and the poisson family? Any pointers are appreciated. Thanks, Lorenz - Lorenz Gygax, Dr. sc. nat. Tel: +41 (0)52 368 33 84 / lorenz.gygax at fat.admin.ch Tag der offenen T??r, 11./12. Juni 2004:

Dear R-mixed-effects-modelers, I could not answer this questions with the book by Pinheiro & Bates and did not find anything appropriate in the archives, either ... We are preparing a short lecture on degrees of freedom and would like to show lme's as an example as we often need to work with these. I have a problem in understanding how many dfs are needed if random terms are used for

I don't think, this has been answered: > I'm trying to run a 3-way within-subject anova in lme with 3 > fixed factors (Trust, Sex, and Freq), but get stuck with handling > the random effects. As I want to include all the possible random > effects in the model, it would be something more or less > equivalent to using aov > > > fit.aov <- aov(Beta ~ >

Dear all, I do not seem to grasp how contrasts are set for ordered factors. Perhaps someone can elighten me? When I work with ordered factors, I would often like to be able to reduce the used polynomial to a simpler one (where possible). Thus, I would like to explicetly code the polynomial but ideally, the intial model (thus, the full polynomial) would be identical to one with an ordered factor.

Dear all, I am doing some data handling and tabualtions and then I am using glmmPQL to fit a binomial hierarchical model (which I assign to a new object). If I do a save.image () or a q ('yes') after this, I get the following warning messages: Warning messages: 1: namespaces may not be available when loading 2: names in persistent strings are currently ignored Sometimes R seems to

I have just realised that I sent this to Per only. For those interested on the list: -----Original Message----- From: Gygax Lorenz FAT Sent: Tuesday, September 14, 2004 4:35 PM To: 'Per Tor??ng' Subject: RE: [R] glmmPQL and random factors Hi Per, > glmmPQL(Fruit.set~Treat1*Treat2+offset(log10(No.flowers)), > random=~1|Plot, family=poisson, data=...) > > Plot is supposed

Dear R-helpers, I'm fighting with the following problem : I want to do bootstrapping on a Kendall correlation with the following code : > cor.function <- function(data,i) cor(data[i, 1], data[i, 2],method="kendall") > boot.ci <- boot.ci(boot.cor <- boot(cbind(x,y),cor.function, R=1000),conf=c(0.95,0.99)) However, I've got problems because I've got ties

Hi all, I'm not quite sure if this is a feature or a bug or if I just fail to understand the documentation: If I use cor() with pairwise.complete.obs and method=pearson, the result is a scalar: ->cor(c(1,2,3),c(3,4,6),use="pairwise.complete.obs",method="pearson") [1] 0.9819805 The documentation says that " '"pairwise.complete.obs"' only

Dear all, I think this question has been raised very recently but I think I didn't see repsonses on the list nor did I find the thread in the archives. (If it is there I'd appreciate directions ...) I am about to install Linux on a Compaq notebook. One important thing I want to do is being able to run R. I have fiddled with different distributions of Linux (LST, SuSE, Debian) and can

Dear all, is this a bug or do a miss something (this concerns version 0.63.1 on Linux)? > boxplot (c (1, 2, 3, 4, 5), ylim= c (-5, 5)) Warning: parameter "ylim" couldn't be set in high-level plot() function > boxplot (c (1, 2, 3, 4, 5), pars= list (ylim= c (-5, 5))) Warning: parameter "ylim" couldn't be set in high-level plot() function > and actually in

Dear R maintainers, R is great. Now that I have that out of the way, I believe I have encountered a bug, or at least an inconsistency, in how Spearman and Kendall rank correlations are handled. Specifically, cor() and cor.test() do not produce the same answer when the data contain NAs. cor() treats the NAs as data, while cor.test() eliminates them. The option use="complete.obs" has

Dear all, Many thanks to all who always so quickly respond with helpful hints! Currently I am working with R 0.63.1 on SuSE 5.2 which I installed this morning within about half an hour: my deepest compliments to the developpers! (I had still 0.62.2 before.) This time I am trying the following: > xy <- list (a= c (1, 2, NA), b= c (2, 3)) > list.name <- "xy" > get

Dear all, I would like to use the biological symbols for male and female as plotting symbols in a scatterplot (ideally filled and non-filled). R does not seem to have these symbols using pch= in plot() nor are they implemented via expression() or at least I did not find them. I found that the symbols are e.g. available in the wasysym and the marvosym package in LaTeX. I have coded two very rough

Dear all, I would like to use the biological symbols for male and female as plotting symbols in a scatterplot (ideally filled and non-filled). R does not seem to have these symbols using pch= in plot() nor are they implemented via expression() or at least I did not find them. I found that the symbols are e.g. available in the wasysym and the marvosym package in LaTeX. I have coded two very rough

i can see source code of function > cor function (x, y = NULL, use = "everything", method = c("pearson", "kendall", "spearman")) { na.method <- pmatch(use, c("all.obs", "complete.obs", "pairwise.complete.obs", "everything", "na.or.complete"))

Dear all, well, today I just seem to run into these problems ... (I am still working on R 0.63.1 on a SuSE 5.2). I would like to have a data.frame that also contains character (and NOT factor) vectors. Two things that I tried (the second worked in R 0.62.2): > test.df <- data.frame (X= character (4)) > test.df$X [1] <- "a" Warning: invalid factor level, NAs generated or:

Dear all, I would like to fit an lm in which a subset of the explanatory variables are linearly dependent. Thus I would like to include the restriction that all betas of these variables sum to 1. Is there a way to this in R? Or is this what happens automatically if I set singular.ok= T (which is the default, I believe)? Thanks for your help. Lorenz --

Dear all, I am trying to use ace on a 446 x 14 Matrix, with two categorical variables in the first two columns. If I try to run it I get: > aceiH <- ace (data.mat, resp, cat= 1:length(x.cat)) Error: NAs in foreign function call (arg 3) There is only one .Fortran call in ace () with the third argument being x = t(x). Thus I tried to debug ace, i.e. I went through ace until just before

Dear all, in a current project I have a pretty huge .Rdata. Thus I was working with R --vsize 100 --nsize 1000000. Today when I tried to restart R I get the following error message: Error: a read error occured Fatal error: unable to restore saved data (remove .RData or increase memory) I increased memory up to --vsize 180 and --nsize 2000000, but the error reoccurrs. Is there a way to know

R: I got a warning message when running the cor.test function using both Spearman and Kendall rank correlations saying that the p-value may be incorrect due to ties in the data. My data has 35 obs and one series has 6 pairs of ties. Does anyone know if this would likely have a great effect on the p-values calculated.. The values look good; tau = -0.68 with p-value = 8e-9 and rho = =0.84