Hello all!
I am running a logistic regression by including fixed effects. The code I use is as follows:
logit y x i.yearcountry,cl(firm)
Where i.ab is constructed using year*country. However, stata tells me "matsize too small". I know that we have code "reghdfe" for OLS regressions, which allows us to have a large dummy control.
Does anyone know how to deal with this kind of problem for logistic regressions? Thanks!
Best wishes,
C
0 Response to "matsize too small" for logistic regressions
Post a Comment