A TEST OF MISSING COMPLETELY AT RANDOM FOR LONGITUDINAL DATA WITH MISSING OBSERVATIONS

Authors
PARK T LEE SY
Citation
T. Park et Sy. Lee, A TEST OF MISSING COMPLETELY AT RANDOM FOR LONGITUDINAL DATA WITH MISSING OBSERVATIONS, Statistics in medicine, 16(16), 1997, pp. 1859-1871
Citations number
18
Categorie Soggetti
Statistic & Probability","Medicine, Research & Experimental","Public, Environmental & Occupation Heath","Statistic & Probability","Medical Informatics
Journal title
Statistics in medicine → ACNP
ISSN journal
02776715
Volume
16
Issue
16
Year of publication
1997
Pages
1859 - 1871
Database
ISI
SICI code
0277-6715(1997)16:16<1859:ATOMCA>2.0.ZU;2-G
Abstract
Liang and Zeger proposed a generalized estimating equations approach t o the analysis of longitudinal data Their models assume that missing o bservations are missing completely at random in the sense of Rubin. Ho wever, when this assumption does not hold, their analysis may yield bi ased results. In this paper, we develop a simple and practical procedu re for testing this assumption. The proposed procedure is related to t hat of Park and Davis. (C) 1997 by John Wiley & Sons, Ltd.