2 GRAPHICAL TECHNIQUES USEFUL IN DETECTING CORRELATION STRUCTURE IN REPEATED-MEASURES DATA

Citation
Ks. Dawson et al., 2 GRAPHICAL TECHNIQUES USEFUL IN DETECTING CORRELATION STRUCTURE IN REPEATED-MEASURES DATA, The American statistician, 51(3), 1997, pp. 275-283
Citations number
16
Categorie Soggetti
Statistic & Probability","Statistic & Probability
Journal title
ISSN journal
00031305
Volume
51
Issue
3
Year of publication
1997
Pages
275 - 283
Database
ISI
SICI code
0003-1305(1997)51:3<275:2GTUID>2.0.ZU;2-A
Abstract
Analysis of repeated measures data using a mixed model includes specif ying a form for the covariance matrix of the within-subject observatio ns. This reduction in the number of estimated parameters from the unsp ecified structure may improve the efficiency of inferences made. An im plementation of this technique has been incorporated in the MIXED proc edure of the SAS(R) statistical package, and includes a wide range of options for the structure of the covariance matrix. It is demonstrated that, draftman's display plots and/or plots in a coordinate system wi th parallel axes can aid in visualizing the dispersion structure.