similar to: An AIC model selection question

Dear all, For an introductory course on glm?s I would like to create an example to show the difference between glm and transformation of the response. For this, I tried to create a dataset where the variance increases with the mean (as is the case in many ecological datasets): poissondata=data.frame( response=rpois(40,1:40), explanatory=1:40) attach(poissondata) However, I have run into

Dear all, How can I replace text in objects that are of class "formula"? y="a * x + b" class(y)="formula" grep("x",y) y[1] Suppose I would like to replace the "x" by "w" in the formula object "y". How can this be done? Somehow, the methods that can be used in character objects do not work 1:1 in formula objects... Many

Dear R users, Suppose I have a set of 10 candidate models, and these all differ by a delta-AIC of 5. Would it be sensible, then, to choose the best-fit model as the one that has *both* minimal AIC *and* minimal number of d.f.? Are there any references for such an approach? Many thanks for your help! Best wishes, Christoph -- Dr. rer.nat. Christoph Scherber University of Goettingen DNPW,

Dear R users, Let?s say I have 10 models, each named m1,m2,m3..., and I would like to summarize them automatically and simultaneously - e.g., to extract parameter estimates later on from all models; how can I do that? I have tried: x=1:10 #this creates some example data y=rnorm(10) m1=lm(x~y) m2=lm(x~1) sum.lms=function(x)summary(paste("m",x,sep="")) sum.lms(1:2) but

Dear all, Suppose I have a nested, repeated measure lme model. Which of the following formulae is correct? (assuming data are sampled from several plots in an agricultural experiment) (1) y~explanatory.variables,random=~time|block/plot/subplot/individual (2) y~explanatory.variables,random=~time|unique.ID.of.every.individual I have read that (2) is the only approach that works. But how could I

Dear all, Is there a way to retrieve standard errors from nls models? The help page tells me that arguments such as se.fit are ignored... Many thanks and best wishes Christoph -- Dr. rer.nat. Christoph Scherber University of Goettingen DNPW, Agroecology Waldweg 26 D-37073 Goettingen Germany phone +49 (0)551 39 8807 fax +49 (0)551 39 8806 Homepage http://www.gwdg.de/~cscherb1

Dear all, How can I extract the total and residual d.f. from a gnls object? I have tried str(summary(gnls.model)) and str(gnls.model) as well as gnls(), but couldn?t find the entry in the resulting lists. Many thanks! Best wishes Christoph -- Dr. rer.nat. Christoph Scherber University of Goettingen DNPW, Agroecology Waldweg 26 D-37073 Goettingen Germany phone +49 (0)551 39 8807 fax +49

Dear R users, suppose I have a matrix of observations for which I calculate all pair-wise correlations: m=matrix(sample(1:100,replace=T),10,10) w=cor(m,use="pairwise.complete.obs") How do I extract only those correlations that are >0.6? w[w>0.6] #obviously doesn?t work, and I can?t find a way around it. I would very much appreciate any help! Best wishes Christoph (using R

Dear R users, I am analyzing several response variables (all scaled to [0;1]) using a multivariate linear model. After fitting the model, I set up a hypothesis matrix to test specific contrasts for these response variables; for example: "a always increases significantly more than b when regressed against x". What I am stuck with now is how to calculate the correct F-values (and

Dear all, I am fitting a multivariate linear model with 7 response variables and 1 explanatory variable. The following matrix P: P <- cbind( c(1,-1,0,0,0,0,0), c(2,2,2,2,2,-5,-5), c(1,0,0,-1,0,0,0), c(-2,-2,0,-2,2,2,2), c(-2,1,0,1,0,0,0), c(0,-1,0,1,0,0,0)) should consist of orthogonal elements (as can be shown using %*% on the individual columns). However, when I use

Dear all, I am forced to work in an environment without administrator rights. When using R2.13.1 on Windows 7 (64-Bit), I found that I can?t install or update any packages due to missing writing permissions. I managed to get full access to a directory on my C:\ drive now - but how do I specify that all libraries shall be installed into this directory? In Rcmd_environ I have the following

Dear all, Is it possible to create a pdf file with layers using the pdf() device in R? Many thanks for your help! Christoph (using R 2.15.1 on Windows 7 64-Bit) -- PD Dr Christoph Scherber Georg-August University Goettingen Department of Crop Science Agroecology Grisebachstrasse 6 D-37077 Goettingen Germany phone 0049 (0)551 39 8807 fax 0049 (0)551 39 8806 http://www.gwdg.de/~cscherb1

Hi, I'm trying to compare models, one of which has all parameters fixed using offsets. The log-likelihoods seem reasonble in all cases except the model in which there are no free parameters (model3 in the toy example below). Any help would be appreciated. Cheers, Jarrod x<-rnorm(100) y<-rnorm(100, 1+x) model1<-lm(y~x) logLik(model1) sum(dnorm(y, predict(model1),

Dear R users, i'm using a custom function to fit ancova models to a dataset. The data are divided into 12 groups, with one dependent variable and one covariate. When plotting the data, i'd like to add separate regression lines for each group (so, 12 lines, each with their respective individual slopes). My 'model1' uses the group*covariate interaction term, and so the coefficients

Hi (R 2.13.1, OSX 10.6.8) I am trying to use predict.rma with continuous and categorical variables. The argument newmods in predict.rma seems to handle coviariates, but appears to falter on factors. While I realise that the coefficients for factors provide the answers, the goal is to eventually use predict.rma with ANCOVA type model with an interaction. Here is a self contained example

Hello, I am using the following model model1=lmer(PairFrequency~MatingPair+(1|DrugPair)+(1|DrugPair:MatingPair), data=MateChoice, REML=F) 1. After reading around through the R help, I have learned that the above code is the right way to analyze a mixed model with the MatingPair as the fixed effect, DrugPair as the random effect and the interaction between these two as the random effect as well.

I am running an lme model with the main effects of four fixed variables (3 continuous and one categorical – see below) and one random variable. The data describe the densities of a mite species – awsm – in relation to four variables: adh31 (temperature related), apsm (another plant feeding mite) awpm (a predatory mite), and orien (sampling location within plant – north or south). I have read

I have a question about how to compare a GLM with a GAM model using anova function. A GLM is performed for example: model1 <-glm(formula = exitus ~ age+gender+diabetes, family = "binomial", na.action = na.exclude) A second nested model could be: model2 <-glm(formula = exitus ~ age+gender, family = "binomial", na.action = na.exclude) To compare these two GLM

I am using anova.lm to compare 3 linear models. Model 1 has 1 variable, model 2 has 2 variables and model 3 has 3 variables. All models are fitted to the same data set. anova.lm(model1,model2) gives me: Res.Df RSS Df Sum of Sq F Pr(>F) 1 135 245.38 2 134 184.36 1 61.022 44.354 6.467e-10 *** anova.lm(model1,model2,model3) gives

Dear all, I was wondering if anyone could help solve a problem of a missing interaction effect!! I carried out a 2 x 2 factorial experiment to see if eggs from 2 different locations (Origin = 1 or 2) had different hatching success under 2 different incubation schedules (Treat = 1 or 2). Six eggs were taken from 10 females (random = Female) at each location and split between the treatments,