Confirmatory Factor Analyses of Multitrait-Multimethod Data: Many Problems and a Few Solutions

摘要: During the last 15 years there has been a steady in crease popularity and sophistication of con firmatory factor analysis (CFA) approach to multitrait- multimethod (MTMM) data. This approach, however, incurs some important problems, most serious being ill-defined solutions that plague MTMM stud ies assumption so-called method factors reflect primarily influence effects. In three different studies, were frequent alternative parameterizations de signed solve this problem tended mask symp toms instead eliminating prcblem. More impor tantly, apparently represented trait variance addition to, or of, var iance for at least models all studies. Further support counterinterpretation was found when external validity crite ria added correlated with factors. problem, it exists, ...