A test for Kronecker product structure covariance matrix

We propose a test for a covariance matrix to have Kronecker Product Structure (KPS). KPS implies a reduced rank restriction on a certain transformation of the covariance matrix and the new procedure is an adaptation of the Kleibergen and Paap (2006) reduced rank test. To derive the limiting distribu...

Full description

Bibliographic Details
Main Authors: Guggenberger, P, Kleibergen, F, Mavroeidis, S
Format: Working paper
Language:English
Published: University of Oxford 2021
_version_ 1826290959904669696
author Guggenberger, P
Kleibergen, F
Mavroeidis, S
author_facet Guggenberger, P
Kleibergen, F
Mavroeidis, S
author_sort Guggenberger, P
collection OXFORD
description We propose a test for a covariance matrix to have Kronecker Product Structure (KPS). KPS implies a reduced rank restriction on a certain transformation of the covariance matrix and the new procedure is an adaptation of the Kleibergen and Paap (2006) reduced rank test. To derive the limiting distribution of the Wald type test statistic proves challenging partly because of the singularity of the covariance matrix estimator that appears in the weighting matrix. We show that the test statistic has a χ2 limiting null distribution with degrees of freedom equal to the number of restrictions tested. Local asymptotic power results are derived. Monte Carlo simulations reveal good size and power properties of the test. Re-examining fifteen highly cited papers conducting instrumental variable regressions, we find that KPS is not rejected in 56 out of 118 specifications at the 5% nominal size.
first_indexed 2024-03-07T02:52:10Z
format Working paper
id oxford-uuid:ae09e26d-24fc-4601-8a83-e284defb410c
institution University of Oxford
language English
last_indexed 2024-03-07T02:52:10Z
publishDate 2021
publisher University of Oxford
record_format dspace
spelling oxford-uuid:ae09e26d-24fc-4601-8a83-e284defb410c2022-03-27T03:39:59ZA test for Kronecker product structure covariance matrixWorking paperhttp://purl.org/coar/resource_type/c_8042uuid:ae09e26d-24fc-4601-8a83-e284defb410cEnglishSymplectic ElementsUniversity of Oxford2021Guggenberger, PKleibergen, FMavroeidis, SWe propose a test for a covariance matrix to have Kronecker Product Structure (KPS). KPS implies a reduced rank restriction on a certain transformation of the covariance matrix and the new procedure is an adaptation of the Kleibergen and Paap (2006) reduced rank test. To derive the limiting distribution of the Wald type test statistic proves challenging partly because of the singularity of the covariance matrix estimator that appears in the weighting matrix. We show that the test statistic has a χ2 limiting null distribution with degrees of freedom equal to the number of restrictions tested. Local asymptotic power results are derived. Monte Carlo simulations reveal good size and power properties of the test. Re-examining fifteen highly cited papers conducting instrumental variable regressions, we find that KPS is not rejected in 56 out of 118 specifications at the 5% nominal size.
spellingShingle Guggenberger, P
Kleibergen, F
Mavroeidis, S
A test for Kronecker product structure covariance matrix
title A test for Kronecker product structure covariance matrix
title_full A test for Kronecker product structure covariance matrix
title_fullStr A test for Kronecker product structure covariance matrix
title_full_unstemmed A test for Kronecker product structure covariance matrix
title_short A test for Kronecker product structure covariance matrix
title_sort test for kronecker product structure covariance matrix
work_keys_str_mv AT guggenbergerp atestforkroneckerproductstructurecovariancematrix
AT kleibergenf atestforkroneckerproductstructurecovariancematrix
AT mavroeidiss atestforkroneckerproductstructurecovariancematrix
AT guggenbergerp testforkroneckerproductstructurecovariancematrix
AT kleibergenf testforkroneckerproductstructurecovariancematrix
AT mavroeidiss testforkroneckerproductstructurecovariancematrix