Time Schedule:
Norman Breslow
BIOST 537
Seattle Campus
Introduction to multivariate analysis of survival data using multiplicative models. Application to epidemiologic studies. Familiarity with interpretation and available computer programs gained by analysis of bona fide sets of data and critiques of analyses appearing in the literature. Prerequisite: BIOST 536 or permission of instructor. Offered: jointly with EPI 537; W.
Class description
Analysis of continuous time-to-event data from epidemiological cohort studies with emphasis on estimation of event risks and rates, statistical tests for equality of hazard rates (survival curves) and relative risk regression.
Student learning goals
Estimate survival (cumulative risk) curves using the Kaplan-Meier estimator
Compare two or more survival curves using a log-rank or related test
Fit appropriate Cox regression models to epidemiologic cohort data using STATA
Use graphical and analytic methods to assess the adequacy of the fitted models
Design and analyze data from case-cohort and nested case-control studies
Construct person-years at risk tables and analyze them with Poisson regression
General method of instruction
Lectures are prepared in advance, with hardcopies of the lecture notes distributed in class. Questions from registered students are encouraged. The questions often clarify points on which several students may share the same uncertainty.
Discussion sections conducted by the TAs will be used to discuss STATA examples, homework, and outstanding questions.
Recommended preparation
Biostat/Epi 536 and Biostat 517/518 or Biostat 511/512/513
Class assignments and grading
Weekly assignments will involve application of the statistical methods described in class to clinical and epidemiological data and demonstration of critical thinking in evaluating claims in published articles. Assignments will generally be distributed one week in advance and be due in class the following Thursday. Computer output should be edited to eliminate all irrelevant material and should clearly indicate the answers to the questions posed. Late assignments are not acceptable. Homework keys prepared by the teaching assistant will be posted to the class website.
25% Homework 5% Class participation 20% Midterm 20% Project 30% Final
