Hello,
We are running an IV-probit model with interactions. Unfortunately, in some cases, our model is not converging even after almost 100 iterations, however, we do get results with statistical significance. We can also successfully estimate marginal effects after that.
In this case, can we interpret our results like we would usually, or is there a problem because of lack of convergence?
Looking forward to some advice in this regard. Thanks in advance!
Related Posts with Interpreting Probit results when convergence is not achieved
Coding for one relationship (Add Health WIV). Dropping people with the shortest relationship duration.- Attention: Frank Lobue
- New package kmest on SSC
- Multi-Level Multiple Imputation Margins Help
- psmath2 and rbounds: estimating 'interaction effect' using Propensity Score Matching, and the sensitivity analysis
Subscribe to:
Post Comments (Atom)
0 Response to Interpreting Probit results when convergence is not achieved
Post a Comment