I'm trying to use Stata's built-in commands to estimate a spatial panel model (i.e. I'm using spxtregress, not xsmle). I've successfully spset and xtset my data and linked a shapefile, so I'm able to run regressions with spxtregress. However, Stata is dropping some of my variables, even when no spatial effects are included (i.e. no DV spatial AR1, no IV spatial AR1, and no spatial error). To illustrate, I've shown two regressions below, both of which include the same DV and single IV and do not include spatial effects. The only difference is that in the first model, I use the years 2009-2015 and in the second I use the years 2009-2014. Model 1 works and model 2 doesn't. Also, 2009-2014 works when a different single regressor is included. This can't be a multicollinearity issue because there's only one regressor. What is going on? Please help.

Array
Array