Efficient estimation with missing data and endogeneity
By Bhavna Rai
Econometric Reviews | February 2023
DOI
www.tandfonline.com/eprint/PGKCXSMBEVT8XZPXVERR/full?target=10.1080/07474938.2023.2178089
Citation
Rai, Bhavna. (2023). Efficient estimation with missing data and endogeneity Econometric Reviews www.tandfonline.com/eprint/PGKCXSMBEVT8XZPXVERR/full?target=10.1080/07474938.2023.2178089.
Copyright
Econometric Reviews, 2023
Share:
Abstract
I study the problem of missing values in the outcome and endogenous covariates in linear models. I propose an estimator that improves efficiency relative to a complete cases 2SLS. Unlike traditional imputation, my estimator is consistent even if the model contains nonlinear functions – like squares and interactions – of the endogenous covariates. It can also be used to combine data sets with missing outcome, missing endogenous covariates, and no missing variables. It includes the well-known “Two-Sample 2SLS” as a special case under weaker assumptions than the corresponding literature.

Bhavna Rai is an Assistant Professor of Economics and Public Policy at the Indian School of Business (ISB). Professor Rai is an econometrician. Her current research focuses on developing new and improved methods for dealing with missing data--a ubiquitous problem in empirical work. Her methods span both cross-sectional and panel data, using linear as well as nonlinear models. She is interested in applying these methods to empirical questions in microeconomics. She has also briefly worked on energy and environmental policy issues confronting India and other developing countries.

Professor Rai holds a PhD in Economics from Michigan State University, an MA in Economics from the Delhi School of Economics, and a BA in Economics from Shri Ram College of Commerce.

Bhavna Rai
Bhavna Rai