Testing for serial correlation in hierarchical linear models

ALEJO, JAVIER; MONTES-ROJAS, GABRIEL; SOSA-ESCUDERO, WALTER

JOURNAL OF MULTIVARIATE ANALYSIS

ELSEVIER INC

Año: 2018 vol. 165 p. 101 - 116

0047-259X

This paper proposes a simple hierarchical model and a testing strategy to identify intraclusterbcorrelations, in the form of nested random effects and serially correlated errorbcomponents. We focus on intra-cluster serial correlation at different nested levels, a that has not been studied in the literature before. A Neyman?s framework is used to derive LM-type tests that allow researchers to identify the appropriate level of clustering aswell as the type of intra-group correlation. An extensive Monte Carlo exercise shows that the proposed tests perform well in finite samples and under non-Gaussian distributions.