Explanatory models for relating growth processes

For many purposes, longitudinal data are a great advance over cross-section al data. The opportunities for modelling are enhanced if data for several o ccasions are obtained for a response, y, and at least one time-varying expl anatory variable, x. The article describes, with examples, three modelling approaches when both y and x changeover time. The first - a conditional app roach - relates x to y in a regression framework. Earlier versions of these models were known as two-wave, two-variable (2W2V) 'causal' models. In the second, unconditional approach, growth or change parameters for x and y ar e themselves related in a second stage analysis. The third approach is base d on structural equations modelling. All three approaches can be implemente d in a multi level framework, The article describes how multilevel models c an extend the way we think about the analysis of longitudinal data, and hen ce how more interesting hypotheses about social processes can be modelled.