Drinking patterns within households: The estimation and interpretation of individual and group variables

Levels of alcohol consumption tend to be similar for individuals living in the same household. This may be because: (a) individuals with similar chara cteristics collect in households (correlated effects); (b) individuals in t he same household are influenced by common factors (exogenous effects); and /or (c) the consumption levels of an individual directly influences the con sumption levels of other individuals in the same household (endogenous effe cts). Whichever of these three possibilities is the principal reason underl ying household clustering of consumption levels has important policy implic ations. In this paper we propose a testing strategy to distinguish between the three types of effect in a cross-sectional data-set. Allowing for exoge nous or endogenous effects shows that the significant socio-economic gradie nt in a model containing only individual variables arises because of misspe cification. However, because we find significant evidence of correlated eff ects, we cannot identify whether it is endogenous or exogenous effects whic h give rise to statistically significant group level variables. The results indicate the possible pitfalls of omitting group level influences. (C) 199 8 John Wiley & Sons, Ltd.