I am studying fund performance and trying to regress funds performance on the performance of previous funds by the same PE firm. The data I have is basically panel data, but it is highly unbalanced (some PE firms have only 2 fund in my sample, whilst others have up to 8 and the time intervals between funds are not consistent). I want to include year fixed effects and the standard deviation should be grouped on the firm level in my regressions.

This is the code I have used in STATA: reg FUND_R FUND_R-1 FUND_R-2 i.year, vce(cluster FIRMID) noconstant

The regression output looks solid, but I am still uncertain if this is the right way to do this? I considered using the xtreg with fe option to indicate fixed effects, but I'm new to STATA and don't know how the fact that my data is highly unbalanced affects that


Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Browse other questions tagged or ask your own question.