I'm working with a mixed model for which I have several response measurements for every individual. One goal is to determine the sampling variance/covariance of the fixed effect estimates for a particular trait. This has been relatively straightforward to accomplish. However, I would also like to estimate the sampling covariance of fixed effects across traits (e.g. what is the sampling covariance for the effect estimate of predictor1 on trait1 and the effect estimate of predictor1 on trait2). Question 1: Does this make sense? If so, is it possible?

I found my way to MCMCglmm because of its ability to fit mixed models to multiple response variables. I include an interaction between fixed effects and the trait, so that a separate regression slope can be fitted for each trait for a particular fixed effect. I would like to determine what the sampling variance/covariance is for the fixed effect estimates, but I am having difficulty determining if/where this would be reported. Question 2: Is MCMCglmm a valid option for what I'm trying to accomplish? If so, could you suggest a solution to my issue? If not, could you suggest literature or other R packages that might help?

I should be up front by saying that this is my first post and I am quickly approaching the limits of my stats understanding with this problem.


Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Browse other questions tagged or ask your own question.