Publication Type

Journal Article

Version

acceptedVersion

Publication Date

3-2009

Abstract

We propose a nonparametric test for conditional uncorrelatedness in multiple-equation models such as seemingly unrelated regressions (SURs), multivariate volatility models, and vector autoregressions (VARs). Under the null hypothesis of conditional uncorrelatedness, the test statistic converges to the standard normal distribution asymptotically. We also study the local power property of the test. Simulation shows that the test behaves quite well in finite samples.

Keywords

Conditional heteroscedasticity, Local polynomial estimator, Nonparametric multivariate regression, Seemingly unrelated regressions, Vector autoregressions

Discipline

Econometrics

Research Areas

Econometrics

Publication

Journal of Business and Economic Statistics

Volume

27

Issue

1

First Page

18

Last Page

29

ISSN

0735-0015

Identifier

10.1198/jbes.2009.0002

Publisher

Taylor and Francis

Additional URL

https://doi.org/10.1198/jbes.2009.0002

Included in

Econometrics Commons

Share

COinS