TY - JOUR
T1 - Analysis of multitrait-multimethod matrices
T2 - A two step principal components procedure
AU - Golding, Stephen L.
AU - Seidman, Edward
N1 - Funding Information:
1. This project was partially supported by a grant received from the Research Board of the University of Manitoba and Grant No. MH 22336 from the National Institute of Mental Health awarded to Julian Rappaport and Edward Seidman. The use of the facilities of the University of Illinois Computer Center are also acknowledged. The authors wish to thank Terrence P. Hogan and Michael D. LeBow for their assistance in data collection, Kevin Kingery for his help in data analysis, and Donald R. Peterson for his helpful comments concerning the manuscript.
PY - 1974/10
Y1 - 1974/10
N2 - A relatively simple technique for assessing the convergence of sets of variables across method domains is presented. The technique, two-step principal components analysis, empirically orthogonalizes each method domain into sets of components, and then analyzes convergence among components across domains. The proposed technique is directly compared with Jackson's (1969) multi-method factor analysis (which involves an a priori orthogonalization) in the analysis of data from personality, vocational interest and aptitude domains. While Jackson's technique focuses on individual variables, and the two-step procedure focuses on the components of variable domains, both techniques produced evidence of cross-domain convergence. However, Jackson's method was found to have several undesirable mathematical and interpretational consequences, while the two-step procedure appears to be a promising technique for the systematic, empirical analysis of multitrait-multimethod matrices.
AB - A relatively simple technique for assessing the convergence of sets of variables across method domains is presented. The technique, two-step principal components analysis, empirically orthogonalizes each method domain into sets of components, and then analyzes convergence among components across domains. The proposed technique is directly compared with Jackson's (1969) multi-method factor analysis (which involves an a priori orthogonalization) in the analysis of data from personality, vocational interest and aptitude domains. While Jackson's technique focuses on individual variables, and the two-step procedure focuses on the components of variable domains, both techniques produced evidence of cross-domain convergence. However, Jackson's method was found to have several undesirable mathematical and interpretational consequences, while the two-step procedure appears to be a promising technique for the systematic, empirical analysis of multitrait-multimethod matrices.
UR - http://www.scopus.com/inward/record.url?scp=4043097094&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=4043097094&partnerID=8YFLogxK
U2 - 10.1207/s15327906mbr0904_7
DO - 10.1207/s15327906mbr0904_7
M3 - Article
AN - SCOPUS:4043097094
SN - 0027-3171
VL - 9
SP - 479
EP - 496
JO - Multivariate Behavioral Research
JF - Multivariate Behavioral Research
IS - 4
ER -