With LM and GLM the predict function can return the standard error for the predicted values on either the observed data or on new data. This is then used to draw confidence or prediction intervals around the fitted regression lines. The confidence intervals (CI) focus on the regression lines and can be interpreted as (assuming … Continue reading Confidence Intervals for prediction in GLMMs

# Tag: GLMM

[UPDATE: I modified a bit the code of the function, now you do not need to pass as character the random effect terms] [UPDATE 2: I added some lines to pass glmer.nb models to the functions, be aware that passing such models to the function will take quite some computing time] [UPDATE 3: you can … Continue reading Generating ANOVA-like table from GLMM using parametric bootstrap

Setting the right random effect part in mixed effect models can be tricky in many applied situation. I will not talk here about choosing whether a grouping variable (sites, individuals …) should be included as a fixed term or as a random term, please see Gelman and Hill (2006) and Zuur et al (2009) for … Continue reading Using bootMer to do model comparison in R

I had a nice workshop two weeks ago in Tübingen (south-germany) concerning Generalized Linear Mixed Models (GLMM) in R. The course was given by two ecologist: Dr. Pius and Fränzi Korner-Nievergelt that spend now half of their time doing statistical consulting (http://www.oikostat.ch/navigation_engl.htm). Nice reference concerning GLMMs are: the 2009 Bolker paper (paper), the 2007 book … Continue reading Generalized Linear Mixed Models in Ecology and in R

R square is a widely used measure of model fitness, in General Linear Models (GLM) it can be interpreted as the percent of variance in the response variable explained by the model. This measure is unitless which makes it useful to compare model between studies in meta-analysis analysis. Generalized Linear Mixed models (GLMM) are extending … Continue reading Computing R square for Generalized Linear Mixed Models in R