Core Seminar Series

Core Seminars

The Applied Biostatistics Seminar Series consists of a series of talks with the primary purpose of furthering statistical knowledge on an applied level. Talks will focus on advances in biostatistical methods and statistical programming techniques and their translation into addressing biomedical research questions. The seminars are open to all members of the Duke community, but primarily geared toward applied statistical researchers.

BCTIP Presentations

Friday, September 15, 2017 - 12:30 at Hock Plaza 11025

Masters Students Yuhui Sun, Aijing Gao, Xi Wang and Leigh Nicholl will present. Yuhui Sun Aijing Gao Xi Wang Leigh Nicholl
Read More

BCTIP Presentations

Friday, September 8, 2017 - 12:30 at Hock Plaza 11th Floor #11025

Masters Students Laurel Jiang, Wen Fan, Karine Yenokyan and Yi Ren will present. Laurel Jiang Wen Fan Karine Yenokyan Yi Ren
Read More

New Weighting Methods

Thursday, August 17, 2017 - 01:30 at North Pavillion, Lower Level Lecture Hall

This session will cover the weighting methodology for comparative effectiveness research in both randomized trials and observational studies. We will present a general class of weighting methods that is readily adaptive to specific study goals. Besides the standard inverse probability weighting (IPW) methods, we will introduce the recently developed methodology...
Read More

Don't Count on it: Assumptions and Pitfalls of Count Regression Models

Friday, August 11, 2017 - 01:30 at Hock Plaza 11025

Count data is widely used in scientific research; for example, in studying the number of disease cases arising in a population. A variety of statistical models exist for analyzing such data. In general, count models constitute a means of describing how and when a series of events occurs to individuals;...
Read More

Causal Inference with Models

Wednesday, August 9, 2017 - 01:30 at North Pavilion Lower Lecture Hall

This session will add models to everything you learned in Chapters 1-5. Instead of having very simple data, with 1 or 2 confounders, we usually have many confounders. It is not possible to model the propensity (probability of treatment) or outcome non-parametrically. Instead, we fit models. We will see how...
Read More