Stata: panel data analysis with ordered logistic regression via 'xtologit' command - Fixed effects possible?

[Maxi Wiedera]

Hello,

I am using using Stata 15 for a panel data analysis. Because I have an ordered variable as DV I want to perform an ordered logistic regression. Now, I have a general question regarding the 'xtologit' command for panel data regressions.

In Stata, it is not possible to to set the option FE for fixed-effects in combination with the command. What is the intuition behind this? Is it generally possible to perform fixed effect regressions or is there a fundamental problem?

xtologit Y X, fe
Stata replies: 'option fe not allowed'

Can someone explain this to me? Thanks!

[Yanis Rahmouni]

In case you are looking for an alternative, there is a community-contributed command called -feologit-, which is from the Stata Journal. I do not know if it works with Stata 15 though.

Baetschmann, G., Ballantyne, A., Staub, K. E., & Winkelmann, R. (2020). feologit: A new command for fitting fixed-effects ordered logit models. The Stata Journal, 20(2), 253-275.

[Maxi Wiedera]

Thank you very much for this hint! I willl test it