Hello,
Hypothetically, I am running X+control+FE on TFP using repeated cross-sectional data. Resultantly, the OLS results appear negative and highly significant despite changing FE. Pertinent literature shows both + & - results.
next scenario:
1. Interacting X*Z give positive and significant results. while interesting X*Z*Y give negative results.
2. Onwards, as a robustness check, the IV GMM results appear positive and highly significant: IV validation, Underidentification test P-values 0.00; while Hansen J statistic p-values 0.3421 showing the validity of IV(?).
how can I go with the interpretation of such scenario? or what should I look for alternatively ?
Thanks,
Naimat
Hypothetically, I am running X+control+FE on TFP using repeated cross-sectional data. Resultantly, the OLS results appear negative and highly significant despite changing FE. Pertinent literature shows both + & - results.
next scenario:
1. Interacting X*Z give positive and significant results. while interesting X*Z*Y give negative results.
2. Onwards, as a robustness check, the IV GMM results appear positive and highly significant: IV validation, Underidentification test P-values 0.00; while Hansen J statistic p-values 0.3421 showing the validity of IV(?).
how can I go with the interpretation of such scenario? or what should I look for alternatively ?
Thanks,
Naimat
