Model-fitting approaches to the analysis of human behaviour

Abstract

Model-fitting methods are now prominent in the analysis of human behavioural variation. Various ways of specifying models have been proposed. These are identical in their simplest form but differ in the emphasis given to more subtle sources of variation. The biometrical genetical approach allows flexibility in the specification of non-additive factors. Given additivity, the approach of path analysis may be used to specify several environmental models in the presence of assortative mating. In many cases the methods should yield identical conclusions. Several statistical methods have been proposed for parameter estimation and hypothesis testing. The most suitable rely on the method of maximum likelihood for the estimation of variance and covariance components. Any multifactorial model can be formulated in these terms. The choice of method will depend chiefly on the design of the experiment and the ease with which a data summary can be obtained without significant loss of information. Examples are given in which the causes of variation show different degrees of detectable complexity. A variety of experimental designs yield behavioural data which illustrate the contribution of additive and non-additive genetical effects, the mating system, sibling and cultural effects, the interaction of genetical effects with age and sex. The discrimination between alternative hypotheses is often difficult. The extension of the approach to the analysis of multiple measurements and discontinuous traits is considered.