SUMMER WORKSHOP ON
MODERN APPLIED METHODS IN BIOSTATISTICS
at the University of Toronto, Medical Science Building
August 14 -17, 2006 -- 9 AM to 5 PM

Lecture 1: REGRESSION METHODS

In 1984, it was suggested by D.A. Preece that at least 100,000 multiple regression analyses were performed per day, but that very few of these were "sensible and worthwhile". Focussing on the case of a single continuous response and multiple predictor variables that can be continuous or categorical, this lecture and laboratory will focus on how to perform sensible multiple linear regression analyses. Discussion will include deciding which variables to include and in what form, model evaluation, overfitting and shrinkage, and model validation.

Instructor: Alison L. Gibbs,
Department of Statistics, University of Toronto
Since completing her PhD in statistics, Alison has held faculty positions at York University and the University of Toronto. She is currently a Senior Lecturer in Statistics and Faculty Advisor to the Statistical Consulting Service in the Department of Statistics at the University of Toronto, where her focus is on teaching applied statistics and training graduate students in statistical consulting. She has collaborated with colleagues across the university, particularly in sleep research and nutritional science.

---

Back to Summer Workshop Index