Behavior &Mtic.r, Vol. 21), No.5, 1990 Alternative Common Factor Models for Multivariate Biometric Analyses J. J. McArdle 1 and H. H. Goldsmith 2 Received" Apr. 1988-Fina115 May 1990 In prior research. we have shown how linear structural equatwn models and Computer programs (e.g., LlSREL) may be simply tmd directly used to prollide alternative.r for the traditional biometric twin design. We use structural equa- tions and path models to define bwrnetrU: group differences, we write traditional common-factor models in. the same way, aJU1 then we take a detailed look at some alternative multivariate and biometric models. We contrast the biometric- factors covariance structure approach used by Loehlin and Vandenberg (1968), Martin and Eaves (1977), arid others with the psychometric-factors approach used try McArdle et at. (1980) aM others. We use the multivariate primary mental abilities data on nwnozygotic (MZ) and dizygotic (DZ) twins from weMin and Vandenberg (1968) to detail fwuiamental differences in model specijicatWn find results. We wend both multivariote biometric approaches using exploratory and confirmatory multiple-factor models. These comparisons show that each alternative multivariate methodology has useful features for empirical applica- tions: KEY WORDS: twins; multiV1lrlste; faclor slmctllral equation models; LISREL; RAM; intelligence; primary mental abilltlcs. INTRODUCTION One of the key insights of evolutionary genetics is that diversity plays an im- portant role in the adaptation of species. This may be true of model building in behavioral genetics as well. For Martin and Eaves (1977) begin their This rese.!.rch bas been supported by granlS from the National !nstltutt on Aglng (AGQ2695, AG04704, and AGa1137) to McArdle, and a Research Career Devclopmenl Awlltd (HD00694) 10 Goldsmith. ,Department of Psychology, University of Virginia, Ottirlollesvillc, Vlrglllia 22903. , Department of P,ychology, University of Oregon, Eugene, Oregon 974tJ3. 569 0OOl-824419O/()9[)(l...(J569$OO.{)()/!l 0 t990 Publishing Col]loration