I have an unbalanced panel data and would like to know which method is better for estimation if I want to capture the heterogeneity of the sample using the plm package or lme4. The sample have year variable, firms id variable, bhoth are using for the index in plm model, also there are location variables that I can use in the lmer function as random intercept.
Then I have the next question:
If I use panel data techniques (plm). To decide between fixed or random effects I run a Hausman test where the null hypothesis is that the preferred model is random effects vs. fixed effects (Green, 2008). The Hausman test in R indicates that the random effect is inconsistent.
If I use random intercept models like lmer::lme4 and make a LRT, then I see that there are a groups effect and the random effect is significant.
I have doubts about which is the correct approach.
Thanks for any help and sorry for the format mistakes.
