I am trying to run a poisson fixed panel effects regression using xtpoisson on Stata where my outcome variable is a binary variable. For a majority of my units, the outcome variable = 0 for the entire duration of my panel. However, when I run a xtpoisson, Stata automatically omits all such units. I have the same problem when I run a xtlogit. When I run a standard fixed effect panel with there is no such problem.

How do I make the xtpoisson regression work without Stata automatically omitting my units with my outcome values equal to 0. I understand that in a fixed effect regression, the regression will automatically drop all regressors which has constant values for all values of any given unit in a panel. However, I dont get why this is the case for an outcome variable. For instance, if my outcome variable is whether or not someone is infected or not (dInfected), then Stata basically drops everyone who is not infected at all for the duration for the panel. But the value of the regressors that yields a not infected outcome, are still of interest to me.


1 Answer 1


With fixed effects you base your conclusions only on comparisons within a unit. If unit does not change, then in many nonlinear models that unit adds nothing, and should thus be ignored. This is the trade-off that comes with fixed effects regressions: on the one hand you are more likely to compare like with like, on the other hand you throw away all the information you could have gotten from comparing across units. So, the problem is not Stata but your choice of using a fixed effects model.

  • $\begingroup$ I think my question was not clear enough, so I have editted it. I understand why having a particular unit have the same value for a given regressor invalidates the fixed effect model, but not entirely sure of why that is the case for the outcome variable. Thank you for your help! $\endgroup$ Apr 16 at 13:20
  • $\begingroup$ I understood that you were only talking about the dependent variable, so my answer does not change. $\endgroup$ Apr 16 at 17:06
  • $\begingroup$ Why is it that this is not an issue for linear models? I dont think I entirely understand. Thank you so much for your help! $\endgroup$ Apr 16 at 18:17
  • $\begingroup$ Please see stats.meta.stackexchange.com/questions/6304/my-upvoting-policy, when you find a question sufficiently clear to write an answer, consider to upvote the question! $\endgroup$ Apr 21 at 15:06

Your Answer

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

Not the answer you're looking for? Browse other questions tagged or ask your own question.