0

I do a regression (Y is a dependent variable and X is an independent variable)

OLS gets insignificant results, while the IV regression gets significant results. I based on literature to suggest X is an endogenous variable. I also did Underidentification test, Weak identification test, Sargan test and endogeneity test (used ivreg2, ivregress and estate endog). The results of these tests all supported my IV regression

How can I interpret the results?

Thanks for your help.

minh minhaof
  • 1
  • I'm puzzled how you ran an IV analysis. It's not a bivariate procedure. – AdamO May 19 '21 at 05:03
  • I have a feeling something has gone wrong. See this answer for example: https://stats.stackexchange.com/questions/45520/when-are-the-asymptotic-variance-of-ols-and-2sls-equal – Ariel May 19 '21 at 05:44

0 Answers0