I'm working with dyadic panel data and estimating a Poisson Pseudo Maximum Likelihood (PPML) gravity model. Two variables I suspect to be endogenous (let's call them var1 and var2) are initially regressed on several institutional predictors using OLS. I then use the residuals in my gravity model.
After that, I construct lagged versions of the residuals to serve as instruments. Here’s the general structure of my code (simplified and anonymized):
# Step 1: Regress var1 and var2 on instruments
ols_1
In a Poisson Pseudo-Maximum Likelihood (PPML) gravity model, endogeneity can be addressed using orthogonalized residuals from first-stage regressions or lagged explanatory variables as instruments, ensuring they're uncorrelated with the error term but strongly correlated with endogenous regressors.
Dear Chuck A Arize ,
Thanks for your reply!
My approach also includes extracting residuals after regressing explanatory variables on potentially endogenous ones. Could you please confirm if this first step is performed using OLS, then the orthogonalized residuals are used in PPML model? Meanwhile, I am unsure of the ways to create IV-PPML, becuase using instruments with fepois (in Rstudio), sounds challenging to me. Could you please advise regarding that as well?
- Badges
- Science topic
- Similar topics
- Mathematics