Testing for Correlation in Error-Component Models

Koen Jochmans

Cambridge Working Papers in Economics from Faculty of Economics, University of Cambridge

Abstract: This paper concerns linear models for grouped data with group-specific effects. We construct a test for the null of no within-group correlation beyond that induced by the group-specific effect. The approach tests against correlation of arbitrary form while allowing for (conditional) heteroskedasticity. Our setup covers models with exogenous, predetermined, or endogenous regressors. We provide theoretical results on size and power under asymptotics where the number of groups grows but their size is held fixed. In simulation experiments we find good size control and high power in a wide range of designs. We also find that our test is more powerful than the popular test developed by Arellano and Bond (1991), which uses only a subset of the information used by our procedure.

Keywords: analysis of variance; clustered standard errors; error components; fixed; heteroskedasticity; within-group correlation; Portmanteau test; short panel data (search for similar items in EconPapers)
JEL-codes: C12 C23 (search for similar items in EconPapers)
Date: 2019-01-25
Note: kj345
References: View references in EconPapers View complete reference list from CitEc
Citations:

Downloads: (external link)
https://www.econ.cam.ac.uk/sites/default/files/pub ... pe-pdfs/cwpe1910.pdf

Related works:
Journal Article: Testing for correlation in error‐component models (2020)
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:cam:camdae:1910

Access Statistics for this paper

More papers in Cambridge Working Papers in Economics from Faculty of Economics, University of Cambridge
Bibliographic data for series maintained by Jake Dyer ().