"initial values not feasible r(1400);" for xtlogit with just DV as time-variant variable

[Antonia Diaz-Valdes]

Hello all, I would really appreciate your help.

I am trying to conduct an xtlogit model for a data with over 5,000 cases at each wave (4 waves), however, the DV is the only measure measured at all time points, while all other IVs and covariates are just measured at time 1. When I run my regression, I am getting this error message
"initial values not feasible r(1400);" I tried the from option after asking for a logit regression and doing the following commands mat a=e(b) mat a1=(a, 0, 0) And then the original model, but I am still having issues. Any thoughts about how to solve this issue for this particular model?

[Phil Bromiley]

You didn't get a quick answer. You'll increase your chances of a useful answer by following the FAQ on asking questions - provide Stata code in code delimiters, readable Stata output, and sample data using dataex. I don't even know exactly what options you used.

If you're trying to run fixed effects, then time invariant variables will mess it up. They are colinear with the fixed effects.