Post Model-Selection inference

Supervisor contact

Related areas

Model selection is important and widely-used tool in applied statistics. However, the problem of how to make inference after selecting the model so that the inference correctly incorporates the uncertainty in the model selection process has proved extremely challenging. This project will review some of the proposed methods. The goal is to understand why the methods propoosed so far struggle to solve the problem.

This project will be co-supervised with Dr Francis Hui.

Updated:  24 June 2017/Responsible Officer:  Director/Page Contact:  School Manager