similar to: mixing nested and crossed factors using lme

Karl, If you use one of the specialized packages to calculate your ICC, make sure that you know what you're getting. (I haven't checked the packages out myself, so I don't know either.) You might want to read David Futrell's article in the May 1995 issue of Quality Progress where he describes six different ways to calculate ICCs from the same data set, all with different

Dear R-ers, I am having trouble understanding why I am getting an error using glmmPQL (library MASS). I am getting the following error: iteration 1 Error in MEEM(object, conLin, control$niterEM) : Singularity in backsolve at level 0, block 1 The long story: I have data from an experiment on pairwise comparisons between 3 treatments (a, b, c). So a typical run of an experiment

It sounds as thought you are interested in Hoyt's Anova which is a form of generalizability theory. This is usually estimated using by getting the variance components from ANOVA. > -----Original Message----- > From: r-help-bounces at stat.math.ethz.ch > [mailto:r-help-bounces at stat.math.ethz.ch] On Behalf Of Karl Knoblick > Sent: Tuesday, May 16, 2006 6:10 AM > To: r-help at

Hi, I'm essentially wanting to calculate intra- and inter-observer variabilities for the first principal component of an optic disc shape measure of a sample of individuals, so from what I can work out I need to work out an intraclass correlation coefficient(s). For the intra-data, I have 2 measurements taken on each individual by the same observer. For the inter-data, 2 observers have taken

Hello! I want to calculate the intra- and interrater reliability of my study. The design is very simple, 5 raters rated a diagnostic score 3 times for 19 patients. Are there methods/funtions in R? I only found packages to calculate interrater variability and intraclass correlation coefficients for matrices of n*m (n subjects, m raters) - I have n subjects, m raters and r repetitions. Can

Hi, all There are 62 samples in my data and I tested 3 times for each one, then I want to use ICC(intraclass correlation) from irr package to test the consistency among the tests. *combatexpdata_p[1:62] is the first text results and combatexpdata_p[63:124] * is the second one and *combatexpdata_p[125:186]* is the third. Here is the result:

Hello dear R help group. I encountered this old thread (http://tinyurl.com/dklgsk) containing the a similar question to the one I have, but left without an answer. I am and hoping one of you might help. A simplified situation: I have a factorial design (with 2^3 experiment combinations), for 167 subjects, each one has answered the same question twice (out of a bunch of "types" of

Hi, I have a data set on germination and plant growth with the following variables: dataset=fm mass (response) sub (fixed effect) moist (fixed effect) pop (fixed effect) mum (random effect nested within population) iheight (covariate) plot (random effect- whole plot factor for split-plot design). I want to see if moist or sub interacts with mum for any of the pops, but I am getting an error

Dear all, I am trying to fit a model with crossed random effects using lme. In this experiment, I have been measuring oxygen consumption (mlmin) in bird nestlings, originating from three different treatments (treat), in a respirometer with 7 different channels (ch). I have also measured body mass (mass) for these birds. id nest treat year mlmin mass ch hack 1EP51711 17

Hi all, I'm trying to test a repeated measures model with random effects using the nlme library. Suppose I have two within subjects factors A, B both with two levels. Using aov I can do: aov.1 <- aov(y ~ A*B + Error(S/(A+B)) following Pinheiro and Bates I can acheive the analagous mixed-effects model with: lme.1 <- lme(y~A*B, random=pdBlocked(list(pdIdent(~1),pdIdent(~A-1),

Douglas Bates wrote: > > The GLMM function in the lme4 package allows you to specify crossed > random effects within the random argument without the need for the > pdBlocked and pdIdent constructions. Simply ensure that your grouping > factors are defined in such a way that each distinct group has a > different level in the grouping factor (this is usually not a problem

Hi R helpers, I'm trying to fit a rather complex model to some simulated data using lme and am not getting the correct results. It seems there might be some identifiability issues that could possibly be dealt with by specifying starting parameters - but I can't see how to do this. I'm comparing results from R to those got when using GenStat... The raw data are available on the

Hi all - R2.0.1, OS X Perhaps while there is some discussion of lme going on..... I am trying to execute a glmm using glmmPQL from the MASS libray, using the example data set from McCullagh and Nelder's (1989, p442) table 14.4 (it happens to be the glmm example for GENSTAT as well). The data are binary, representing mating success (1,0) for crosses between males and females from two

Consider the Assay data where block, sample within block and dilut within block is random. This model can be fitted with (where I define Assay2 to get an ordinary data frame rather than a grouped data object): Assay2 <- as.data.frame(Assay) fm2<-lme(logDens~sample*dilut, data=Assay2, random=list(Block = pdBlocked(list(pdIdent(~1), pdIdent(~sample-1),pdIdent(~dilut-1))) )) Now, block

Hello, I have 50 raters and 180 cases which are rated as malignant, probably malignant, probably benign, and benign. I want to compare all the raters but I want a weighted kappa to penalize differences between malignant and benign more than differences between malignant and probably malignant. I only found the weighted option in the 2-rater functions (kappa2, wkappa, cohen.kappa). The

Hi All: Could anyone point me to a package that can calculate stratified kappa? My design is like this, 4 raters, 30 types of diagnosis scores, 20 patients. Each rater will rate each patient for each type of diagnosis score. The rater's value is nominal. I know I can measure the agreement between raters for each type of diagnosis score, e.g., calculate out 30 kappa values. My problem is I

hello! this is a question, how can i specify the random part in the GLMM-call (of the lme4 library) for compound matrices just in the the same way as they defined in the lme-Call (of the nlme library). For example i would just need random=list(my.Subject=pdBlocked(list(pdIdent(~... , ...),pdIdent(~... , ...)))) this specification , if i also attach library(nlme) , is not

hello! this is a question, how can i specify the random part in the GLMM-call (of the lme4 library) for compound matrices just in the the same way as they defined in the lme-Call (of the nlme library). For example i would just need random=list(my.Subject=pdBlocked(list(pdIdent(~... , ...),pdIdent(~... , ...)))) this specification , if i also attach library(nlme) , is not

I have been using lme from nlme to do a 3-way anova with all the effects treated as random. I was wondering if someone could direct me to an example of how to do this using lmer from lme4. I have 3 main effects, tim, trt, ctr, and all the interaction effects tim*trt*ctr. The response variable is ge. Here is my lme code: dat <-

Try this data(Assay) as1 <- lme(logDens~sample*dilut, data=Assay, random=pdBlocked(list( pdIdent(~1), pdIdent(~sample-1), pdIdent(~dilut-1)))) update(as1,random=pdCompSymm(~sample-1)) update(as1,random=pdCompSymm(~sample-1)) update(as1,random=pdCompSymm(~sample-1)) update(as1,random=pdCompSymm(~sample-1)) I'm