On the usefulness of latent variable causal modeling in testing theories of naturally occurring events (including adolescent drug use): a rejoinder to Martin.

This paper considers the arguments raised by Martin (1982) against the methodologies used by Huba, Wingard, and Bentler (1981) and their subsequent conclusions. Several of Martin's criticisms are the result of a misreading of our paper and selective citations, whereas other criticisms were discussed in the original paper and resolved through alternate forms of data analysis. Further analyses are presented to address issues raised by Martin. Martin's arguments against latent variable models are refuted.