skip to main content skip to footer

A Factor Analysis Approach to Round Robin Designs NSF ANCOVA

Author(s):
Wong, George Y.
Publication Year:
1981
Report Number:
RR-81-53
Source:
ETS Research Report
Document Type:
Report
Page Count:
34
Subject/Key Words:
National Science Foundation (NSF), Analysis of Covariance (ANCOVA), Analysis of Variance (ANOVA), Data Analysis, Factor Analysis, Models, Statistical Analysis

Abstract

We adopt a factor analytic approach to study round robin analysis of variance models appropriate for round robin interaction data with the actor and partner effects of any member involved linearly related. Such models are particularly important both statistically and computationally in sociometric studies on structures of social relationships involving a large number of subjects. We provide a convergent algorithm for computing the maximum likelihood estimates of the variances and covariances associated with these models. We also discuss the posterior inference of the linear effects. A detailed analysis on a set of speech data is worked out using these models. (34pp.)

Read More