Formative measurement models in covariance structure analysis: Specification and identification

Many researchers seem to be unsure about how to specify formative measurement models in software programs like LISREL or AMOS and to establish identification of the corresponding structural equation model. In order to make identification easier, a new, mainly graphically-oriented approach is presented for a specific class of recursive models with formative indicators. Using this procedure it is shown that some models have erroneously been considered underidentified. Furthermore, it is shown that specifying formative indicators as exogenous variables rises serious conceptual and substantial issues in the case that the formative construct is truly endogenous (i. e. influenced by more remote causes). An empirical study on the effects and causes of brand competence illustrates this point.