Sensitivity of a random intercept to level 1 predictors

[John Larsson]

Hello,

This is more of a general question although I am using Stata for my analysis.

In a random intercept model (no level 2 predictors or random slopes), where mu0j is the random component of the intercept, and j the grouping variable, can mu0j be sensitive to the choice of level 1 predictors? I would have thought not since level 1 by definition is for "within" predictors but I would like to know if there are any other reasons why mu0j might depend on level 1 predictors (beyond issues of random sampling variation).

[Phil Bromiley]

You didn't get a quick answer. You'll increase your chances of a useful answer by following the FAQ on asking questions - provide Stata code in code delimiters, readable Stata output, and sample data using dataex. It would help us understand your question if you included code so we know what model you're running and how you're running it.