Open AccessFocused principal component analysis: a promising approach for confirming findings of exploratory analysis?
Author(s) -
Falissard B.,
Corruble E.,
Mallet Luc,
Hardy P.
Publication year - 2001
Publication title -
international journal of methods in psychiatric research
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 1.275
H-Index - 73
eISSN - 1557-0657
pISSN - 1049-8931
DOI - 10.1002/mpr.115
Subject(s) - principal component analysis , variable (mathematics) , set (abstract data type) , field (mathematics) , psychology , correspondence analysis , exploratory analysis , econometrics , matrix (chemical analysis) , principal (computer security) , mathematics , test (biology) , computer science , statistics , data science , paleontology , materials science , composite material , biology , operating system , mathematical analysis , pure mathematics , programming language
Abstract In many psychiatric studies, the objective is to describe and understand relationships between a large set of quantitative variables, with a particular interest in the relationship between one variable (often regarded as a response) and the others (often regarded as explanatory). This paper describes a new method to apply in such situations. It is based on principal components analysis (PCA). Like this technique, it conveys the structure of a correlation matrix into a low‐dimensional diagram but, unlike PCA, it makes it possible to represent accurately the correlations of a given variable with the other variables (and even to test graphically the hypothesis that one of these correlations is equal to zero). Two examples in the field of psychiatry research are provided. Copyright © 2001 Whurr Publishers Ltd.