Hi,

I am running a two-way fixed effects regression and would like to include some economic and demographic variables as controls. The issue is these controls don't exist at the state and year level I need until much later in the time window I am considering. Would it make sense to get a baseline level of these covariates, such as non-white population, and interact it with years in the regression? I have tried to do this using the reghdfe command in Stata but I run into issues. Could anyone help with how to proceed?

Best regards
Ola