Dipartimento di Statistica e Metodi Quantitativi DISMEQ

Valid F-screening in linear regression

The Department of Statistics and Quantitative Methods at Università di Milano-Bicocca is proud to host a seminar featuring Daniela Witten,  Dorothy Gilford Endowed Chair and Professor of Statistics & Biostatistics at the University of Washington.

🗓️ Event Details

  • Date: Wednesday, March 11th

  • Title: Valid F-screening in linear regression

  • Time: 12:30 PM

  • Location: Room U6-32, Building U6, Piazza dell'Ateneo Nuovo, Milan

Abstract: 
Suppose that a data analyst wishes to report the results of a least squares linear regression only if the overall null hypothesis—namely, that all non-intercept coefficients equal zero—is rejected. This practice, which we refer to as F-screening (since the overall null hypothesis is typically tested using an F-statistic), is in fact common practice across a number of applied fields. Unfortunately, it poses a problem: standard guarantees for the inferential outputs of linear regression, such as Type 1 error control of hypothesis tests and nominal coverage of confidence intervals, hold unconditionally, but fail to hold conditional on rejection of the overall null hypothesis. 

In this talk, I will present an inferential toolbox for the coefficients in a least squares model that are valid conditional on rejection of the overall null hypothesis. I will present selective p-values that lead to tests that control the selective Type 1 error, i.e., the Type 1 error conditional on having rejected the overall null hypothesis. Furthermore, they can be computed without access to the raw data, using only the standard outputs of a least squares linear regression, and therefore are suitable for use in a retrospective analysis of a published study. I will also present confidence intervals that attain nominal selective coverage, and point estimates that account for having rejected the overall null hypothesis. 
I will illustrate this selective procedure via re-analysis of a published result in the biomedical literature, for which the raw data is not available. 
 
This is joint work with Olivia McGough (U. Washington) and Daniel Kessler (UNC Chapel Hill). 
 
 

Google meet

Click to join the meeting

 
 

 

Categoria news
Seminari