Department Colloquium - Adam McCloskey

Adam McCloskey, Department of Economics, University of Colorado Boulder

Inference on Winners
 
Many empirical questions can be cast as inference on a parameter selected through optimization.  For example, researchers may be interested in the effectiveness of the best policy found in a randomized trial, or the best-performing investment strategy based on historical data.  Such settings give rise to a winner's curse, where conventional estimates are biased and conventional confidence intervals are unreliable.  This paper develops optimal confidence sets and median-unbiased estimators that are valid conditional on the parameter selected and so overcome this winner's curse. If one requires validity only on average over target parameters that might have been selected, we develop hybrid procedures that combine conditional and projection confidence sets to offer further performance gains relative to existing alternatives.
 

Friday, January 18 at 3:00pm to 4:00pm


Engineering Center, ECCR 265
1111 Engineering Drive, Boulder, CO 80309

Event Type

Colloquium/Seminar

Interests

Science & Technology, Research & Innovation

Audience

General Public

College, School & Unit

Engineering & Applied Science

Group
Applied Mathematics
Subscribe
Google Calendar iCal Outlook