Short T Dynamic Panel Data Models with Individual, Time and Interactive Effects

92 Pages Posted: 12 Feb 2020

See all articles by Kazuhiko Hayakawa

Kazuhiko Hayakawa

Hiroshima University

M. Hashem Pesaran

University of Southern California - Department of Economics; University of Cambridge - Trinity College (Cambridge)

L. Vanessa Smith

University of York - Department of Economics and Related Studies

Date Written: September 2, 2018

Abstract

This paper proposes a quasi maximum likelihood (QML) estimator for short T dynamic fixed effects panel data models allowing for interactive effects through a multi-factor error structure. The proposed estimator is robust to the heterogeneity of the initial values and common unobserved effects, whilst at the same time allowing for standard fixed and time effects. It is applicable to both stationary and unit root cases. Order conditions for identification of the number of interactive effects are established, and conditions are derived under which the parameters are almost surely locally identified. It is shown that global identification is possible only when the model does not contain lagged dependent variables. The QML estimator is proven to be consistent and asymptotically normally distributed. A sequential multiple testing likelihood ratio procedure is also proposed for estimation of the number of factors which is shown to be consistent. Finite sample results obtained from Monte Carlo simulations show that the proposed procedure for determining the number of factors performs very well and the QML estimator has small bias and RMSE, and correct empirical size in most settings. The practical use of the QML approach is illustrated by means of two empirical applications from the literature on cross county crime rates and cross country growth regressions.

Keywords: short T dynamic panels, unobserved common factors, quasi maximum likelihood, interactive effects, multiple testing, sequential likelihood ratio tests, crime rate, growth regressions

JEL Classification: C12, C13, C23

Suggested Citation

Hayakawa, Kazuhiko and Pesaran, M. Hashem and Smith, L. Vanessa, Short T Dynamic Panel Data Models with Individual, Time and Interactive Effects (September 2, 2018). Available at SSRN: https://ssrn.com/abstract=3268434 or http://dx.doi.org/10.2139/ssrn.3268434

Kazuhiko Hayakawa

Hiroshima University ( email )

Japan

M. Hashem Pesaran

University of Southern California - Department of Economics

3620 South Vermont Ave. Kaprielian (KAP) Hall 300
Los Angeles, CA 90089
United States

University of Cambridge - Trinity College (Cambridge) ( email )

United Kingdom

L. Vanessa Smith (Contact Author)

University of York - Department of Economics and Related Studies ( email )

Heslington
University of York
York, YO10 5DD
United Kingdom

Here is the Coronavirus
related research on SSRN

Paper statistics

Downloads
72
Abstract Views
496
rank
365,808
PlumX Metrics