Estimating the Elasticity of Intertemporal Substitution When Instruments Are Weak

In the instrumental variables (IV) regression model, weak instruments can lead to bias in estimators and size distortion in hypothesis tests. This paper examines how weak instruments affect the identification of the elasticity of intertemporal substitution (EIS) through the linearized Euler equation. Conventional IV methods result in an empirical puzzle that the EIS is significantly less than one while its inverse is not different from one. This paper shows that weak instruments can explain the puzzle and reports valid confidence intervals for the EIS using pivotal statistics. The EIS is less than one and not significantly different from zero for eleven developed countries. JEL classification: C12, E21, G12 Forthcoming in The Review of Economics and Statistics ∗Department of Economics, Harvard University. I thank John Campbell for the dataset and computer programs from Campbell (2003). For helpful comments and discussions, I thank John Campbell, Marcelo Moreira, James Stock, Michael Woodford, the referees, and seminar participants at Harvard and the 2002 Econometric Society Australasian Meeting. This paper is based upon work supported under a National Science Foundation Graduate Research Fellowship.