MULTILEVEL COVARIANCE STRUCTURE-ANALYSIS OF INTRA-FAMILIAL SUBSTANCE USE

Conventional covariance structure analysis, such as factor analysis, i s otten applied to data that are obtained in a hierarchical fashion, s uch as parents and siblings observed within families. However, multiva riate modeling of such data are most frequently done as if the data we re obtained as a simple random sample from a single population. An alt ernative specification is presented which explicitly models the within -level and between-level covariance matrices in familial substance use . Results demonstrate homogeneity in substance use within families but heterogeneity across families which could be accounted for by family- level variables of marital status, economic status, and biological rel ationships. It is shown that conventional covariance structure softwar e can be easily adapted to handle hierarchical models, providing a lar ge set of new analysis possibilities for multi-level data. (C) 1997 El sevier Science Ireland Ltd.