This unit covers statistical models for longitudinal and correlated data in medical research. The concept of hierarchical data structures is developed, together with demonstrations of the inadequacy of standard statistical methods. Beginning with models based on normal distributions, more appropriate statistical procedures involving generalised estimating equations (GEE) and mixed linear models are developed. The limitations of traditional repeated measures analysis of variance is demonstrated. Extensions to non-normal outcomes are developed and approaches based on GEE and generalised linear mixed models (GLMM) are developed and contrasted. Throughout, emphasis is placed on interpretation... -- Course Website
Instructor: Associate Professor Gillian Heller
Prerequisites: [BCA808 and BCA809] or [((STAT271 and STAT272) or STAT371 or STAT810) and (STAT411 or STAT811)]