Optimal inference for instrumental variables regression with non-Gaussian errors

Matias D. Cattaneo, Richard K. Crump, Michael Jansson

Research output: Contribution to journalArticle

6 Scopus citations

Abstract

This paper is concerned with inference on the coefficient on the endogenous regressor in a linear instrumental variables model with a single endogenous regressor, nonrandom exogenous regressors and instruments, and i.i.d. errors whose distribution is unknown. It is shown that under mild smoothness conditions on the error distribution it is possible to develop tests which are "nearly" efficient in the sense of Andrews et al. (2006) when identification is weak and consistent and asymptotically optimal when identification is strong. In addition, an estimator is presented which can be used in the usual way to construct valid (indeed, optimal) confidence intervals when identification is strong. The estimator is of the two stage least squares variety and is asymptotically efficient under strong identification whether or not the errors are normal.

Original languageEnglish (US)
Pages (from-to)1-15
Number of pages15
JournalJournal of Econometrics
Volume167
Issue number1
DOIs
StatePublished - Mar 1 2012
Externally publishedYes

All Science Journal Classification (ASJC) codes

  • Economics and Econometrics

Fingerprint Dive into the research topics of 'Optimal inference for instrumental variables regression with non-Gaussian errors'. Together they form a unique fingerprint.

Cite this