On the Estimation and Inference of a Cointegrated Regression in Panel Data

Author(s)/Creator(s)

Chihwa Kao, Syracuse University. Center for Policy ResearchFollow

Description/Abstract

The main contribution of this paper is to add to the literature by suggesting a dynamic OLS (DOLS) estimator and providing a serious comparison of the finite sample properties of the OLS, fully modified OLS (FMOLS), and DOLS estimators in panel cointegrated regression models. Monte Carlo results illustrate the sampling behavior of the proposed estimators and show that (1) the OLS estimator has a non-negligible bias in finite samples, (2) the FMOLS estimator does not improve over the OLS estimator in general, and (3) the DOLS outperforms both the OLS and FMOLS estimators.

Document Type

Working Paper

Date

1999

Keywords

OLS, DOLS, FMOLS, cointegrated regression in panel data, panel data, time-series models, dynamic quantile regressions

Language

English

Series

Working Papers Series

Disciplines

Mathematics

Additional Information

Harvest from RePEc at http://repec.org

Recommended Citation

Kao, Chihwa, "On the Estimation and Inference of a Cointegrated Regression in Panel Data" (1999). Center for Policy Research. 145.
https://surface.syr.edu/cpr/145

Source

Metadata from RePEc