|
Activity Number:
|
111
|
|
Type:
|
Contributed
|
|
Date/Time:
|
Monday, July 30, 2007 : 8:30 AM to 10:20 AM
|
|
Sponsor:
|
Section on Statistical Computing
|
| Abstract - #308286 |
|
Title:
|
Testing of Hypothesis of a Structured Mean Vector for Multilevel Multivariate Data with Structured Correlations on Repeated Measurements
|
|
Author(s):
|
Anuradha Roy*+ and Ricardo Leiva
|
|
Companies:
|
The University of Texas at San Antonio and F.C.E. Universidad Nacional de Cuyo
|
|
Address:
|
Dept of Management Sc and Statistics, San Antonio, TX, 78249,
|
|
Keywords:
|
autoregressive correlation structure ; compound symmetry correlation structure ; equicorrelated (partitioned) variance covariance matrix ; maximum likelihood estimates ; multi-level multivariate data ; multivariate equicorrelation
|
|
Abstract:
|
We study the testing of hypothesis of a structured mean vector against an unstructured mean vector for multilevel multivariate data, where more than one response variable is measured on each experimental unit on more than one site at several time points under the assumption of multivariate normality. We provide the maximum likelihood estimates of the unknown population parameters for both autoregressive of order one and compound symmetry correlation structures on the repeated measures over time. We also provide the computation algorithms for calculating the test statistics. The proposed test is illustrated with four real datasets.
|
