I am just reading this paper: Linear Quantile Mixed Models: The lqmm Packagefor Laplace Quantile Regression. Let us assume I have a repeated observation experiment, where I want to assess the effect of time, some "factor" (say A and B) and interaction between them. The model reports coefficients, but how to test them jointly, in the spirit of the ANOVA deviance table for the GLM? Or how to test the differences between, each time point and the initial time point and report confidence intervals for it? I guess it can be done via bootstrap, but how about the p-values for the main effects?
$\begingroup$
$\endgroup$
1
-
$\begingroup$ By model comparison: fit two models, with and without the effcts you want to test jointly. Then compare the fits. $\endgroup$– kjetil b halvorsen ♦Commented Jul 21, 2020 at 16:02
Add a comment
|