| | |
Summary: A tutorial on Multi-Block Discriminant Correspondence Analysis
(MUDICA): A new method for analyzing discourse data from clinical
populations
Lynne J. Williams
University of Western Ontario
Herv´e Abdi
University of Texas at Dallas
Rebecca French
Southlake Regional Health Care
J.B. Orange
University of Western Ontario
Purpose. In communication disorders research, we frequently describe clinical groups based
on patterns of performance, but we often study only few participants described by many quan-
titative and qualitative variables. These data are difficult to handle by standard inferential tools
(e.g., ANOVA or factor analysis) whose assumptions are unfit for these data. This paper presents
Multi-block Discriminant Correspondence Analysis (MUDICA) which is a recent method that
can handle datasets not suited for standard inferential techniques.
Method. MUDICA is illustrated with clinical data examining conversational trouble-source
repair and topic maintenance in dementia of the Alzheimers type (DAT). Seventeen DAT parti-
cipant/spouse dyads (6 control, 5 early DAT, 6 moderate DAT) produced spontaneous conversa-
|
