I'm running some regression models with panel data from Brazilian municipalities (N = 64,708, Number of groups = 5,561, T = 3).
The results seem ok at first, but:
1. The overall R2 is almost null: 0.0008
2. rho = .9917
3. corr(u_i, Xb) = -0.9928
What do these pieces of information suggest about the convenience of running FE models versus running pooled OLS?
Related Posts with Fixed effects model with high rho and negative corr(u_i, Xb): a problem?
extracting column number based on minimum row value- replace or overwrite existing predicted values
- Modeling heterogeneous group variances
- How to separate an observation entered within an observation and use some of the content
- equality of coefficients test with reghdfe: subsample analysis or interaction terms?
Subscribe to:
Post Comments (Atom)
0 Response to Fixed effects model with high rho and negative corr(u_i, Xb): a problem?
Post a Comment