Modelling Contexuality and Heterogeneity with Multilevel Models

Populations commonly exhibit complex structure with many levels, so that patients (level 1) are assigned to clinics (level 2); while individuals (1) may 'learn' their health-related behaviour in the context of households (2) and local cultures (3). Moreover, survey designs often reflect the population structure. Thus, in a survey of voting, respondents (1) are clustered by constituencies (2).

Multilevel models are currently being applied to a growing number of social science research areas, including educational and organisational research, epidemiology, voting behaviour, sociology, and geography. By using multilevel models we can model simultaneously at several levels, gaining the potential for improved estimation, valid inference and a better substantive understanding of the realities of the social world.

This talk aims to show the potential of multilevel models making the argument without algebra but graphically and through examples.