Applied Survival Analysis

BST 223 Subject & Catalog Number

Description

BST 223 is a course on survival analysis, or more generally time-to-event analysis, with the primary audience being graduate students pursuing a Master’s degree in biostatistics or a PhD in one of the other departments at the Harvard Chan School. Covered in the course will be: an introduction to various types of censoring and truncation that commonly arise; the mathematical representations of time-to-event distributions, such as via the hazard and survivor functions; nonparametric methods such as Kaplan-Meier estimation of the survivor function and log-rank test for hypothesis testing; semi-parametric and parametric regression modeling techniques, such as the Cox model, the accelerated failure time model, the additive hazards model and cure fraction models; survival analysis within the causal inference paradigm; the analysis of competing and semi-competing risks; outcome-dependent sampling schemes, such as nested case-control and case-cohort designs; and, power/sample size calculations for studies with time-to-event endpoints. Throughout, equal emphasis will be given to the theoretical/technical underpinnings of survival analysis and to the use of real world data examples. Coding examples and course support will focus on the statistical software R.

Course Prerequisite(s): BST210 or BST213 or BST 220 or BST 232 or BST 260 or PHS2000A

Course Note: lab or section times to be announced at first meeting.