Detection of influential observations in longitudinal mixed effects regression models.

E.S. Tan*, M.J.N. Ouwens, M.P.F. Berger

*Corresponding author for this work

Research output: Contribution to journalArticleAcademicpeer-review

Abstract

Mixed effects models for longitudinal data with fixed as well as random parameters are often used to describe average profiles. Influence measures are usually constructed to detect influential subjects and observations for the fixed regression parameters, treating the subject-specific parameters as nuisance parameters. One of these measures is the well-known Cook's distance. We show that this statistic may fail to detect or may incorrectly detect influential observations due to the random-effects variances and covariances. A conditional version of Cook's distance is proposed to assess the influence of observations on the estimated regression parameters.
Original languageEnglish
Pages (from-to)271-284
JournalJournal of the Royal Statistical Society. Series D: The Statistician
Volume50
Issue number3
DOIs
Publication statusPublished - 1 Jan 2001

Fingerprint

Dive into the research topics of 'Detection of influential observations in longitudinal mixed effects regression models.'. Together they form a unique fingerprint.

Cite this