Timeline for OLS with clustered standard errors vs. multilevel modeling when the main interest is at the individual level
Current License: CC BY-SA 3.0
2 events
| when toggle format | what | by | license | comment | |
|---|---|---|---|---|---|
| Nov 18, 2013 at 21:16 | comment | added | conjugateprior | A little niggle: I don't think you need a phd in statistics to deal with random effects correlated with regressors by adding averages of individual level covariates as predictors for group level intercepts. This fixes assumption ii) across levels, and if you don't like it within level then you ought to think twice about regression models altogether. | |
| Oct 1, 2012 at 23:13 | history | answered | StasK | CC BY-SA 3.0 |