EPID787: An Introduction To Multilevel Analysis In Public Health
Graduate level
Residential
Summer term(s) for residential students;
1 credit hour(s) for residential students;
Instructor(s): Staff (Residential);
Offered Every Summer
Prerequisites: None
Advisory Prerequisites: Introductory course in epidemiology and an introductory course in statistics (i.e. some familiarity with regression modeling).
Description: This short course will review the rationale for multilevel analysis in public health research, build the statistical theory and practice of these models from the fundamentals of the regression-based approaches and demonstrate a variety of different forms that the models can take, including fixed and random effects, marginal (population average) models and extensions for categorical and survival outcomes. Fitting and interpreting models will be demonstrated using Stata statistical software, and parallel code will also be provided in SAS. Special emphasis will be placed on the strengths and limitations of multilevel analyses in investigating social and group-level determinants of health, and the causal interpretations of estimated parameters.
