MULTITRAIT-MULTIMETHOD MODELS FOR PROFITABILITY INDICATORS

Abstract

A `multitrait-multimethod´ (MTMM) model is used when each of a set of traits is measured by each of a set of methods. The multitrait-multimethod model is an example of a highly specialized measurement part of a structural model. In such a model, variables are generated under a systematic design in which certain methods of measurement are fully crossed with the trait variables intended to be measured. That is, each trait is measured by each of several methods. When this design is applied, factors can be hypothesized to separate the various sources of variance, especially, into trait and method factors. Interest is usually on the trait factors, while the method factors provide an important basis for correlations among variables. Based on the goodness-of-fit of the estimated MTMM model this paper aims at testing both convergent and discriminant validity of several microeconomic financial indicators whether they are reliable measures of different traits of economic profitability measured by different baseline methods.