Welcome to the new version of CaltechAUTHORS. Login is currently restricted to library staff. If you notice any issues, please email coda@library.caltech.edu
Published 1996 | public
Journal Article

Nuisance vs. Substance: Specifying and Estimating Time-Series-Cross-Section Models

Abstract

In a previous article we showed that ordinary least squares with panel corrected standard errors is superior to the Parks generalized least squares approach to the estimation of time-series-cross-section models. In this article we compare our proposed method with another leading technique, Kmenta's "cross-sectionally heteroskedastic and timewise autocorrelated" model. This estimator uses generalized least squares to correct for both panel heteroskedasticity and temporally correlated errors. We argue that it is best to model dynamics via a lagged dependent variable rather than via serially correlated errors. The lagged dependent variable approach makes it easier for researchers to examine dynamics and allows for natural generalizations in a manner that the serially correlated errors approach does not. We also show that the generalized least squares correction for panel heteroskedasticity is, in general, no improvement over ordinary least squares and is, in the presence of parameter heterogeneity, inferior to it. In the conclusion we present a unified method for analyzing time-series-cross-section data.

Additional Information

© 1996 University of Michigan. Thanks to Ross Burkhart and Michael Lewis-Beck for providing data and to Elizabeth Gerber, William Greene, William Heller, Gary King, Andrew Levin, Brian Loynd, James Stimson, Glenn Sueyoshi, and Diana Weinhold for helpful conunents. Katz thanks the National Science Foundation for a Graduate Fellowship funding his work on this project while at UCSD. Part of this article was delivered at the 1993 Annual Meeting of the Midwest Political Science Association, Chicago, Illinois.

Additional details

Created:
August 20, 2023
Modified:
October 26, 2023