Exact Statistical Inference after Model Selection

Feb 25

Tuesday, February 25, 2014

12:30 pm - 2:00 pm
Gross Hall 330


Jason D. Lee, PhD candidate ICME, Stanford

We develop a framework for post-selection inference. At the core of our framework is a result that characterizes the exact (non-asymptotic) distribution of linear combinations/contrasts of truncated normal random variables. This result allows us to (i) obtain honest confidence intervals for the selected coe. I am a 4th year graduate student in Computational Math advised by Trevor Hastie. Previously, I received a BS in Mathematics from Duke University. I am a native of Cupertino, CA and attended Lynbrook High School. My current interests are in Statistics, Machine Learning, and Optimization. My main focus is on developing and analyzing algorithms for the analysis of large and high-dimensional data. My work uses tools from Statistics, Convex Optimization, Machine Learning, and Probability. 12:30pm lunch, 1:00pm lecture


Peterson, Kathy