|
|
Article: Random-effects model for multiple characteristics with possibly missing data.
- Article from:
- Journal of the American Statistical Association
- Article date:
- June 1, 1997
- Author:
CopyrightCOPYRIGHT 1997 American Statistical Association. This material is published under license from the publisher through the Gale Group, Farmington Hills, Michigan. All inquiries regarding rights should be directed to the Gale Group. (Hide copyright information)
|
1. INTRODUCTION
Analysis of longitudinal studies in which a single characteristic is measured at n different occasions has been considered by many authors, including Grizzle and Allen (1969), Khatri (1966), Potthoff and Roy (1964), and Rao (1965). They have all considered the timing of observations to be the same for all units and made no allowance for missing data. The case of arbitrary measurement times and variation in the number of observations for different individuals has been considered by Laird and Ware (1982), who used a random-effects approach. An extension to multiple characteristics in which a random-effects model for the covariance structure is assumed ...