Online Program Home
  My Program

Abstract Details

Activity Number: 384 - Bayes, Frequentist, Fiducial: BFF in Action
Type: Invited
Date/Time: Tuesday, August 1, 2017 : 2:00 PM to 3:50 PM
Sponsor: General Methodology
Abstract #321997
Title: Combining Diverse Information Sources with the II-CC-FF Paradigm
Author(s): CĂ©line Cunen* and Nils Lid Hjort
Companies: University of Oslo and University of Oslo
Keywords: combination of information ; confidence distributions ; focused fusion ; meta-analysis
Abstract:

Combining information across different sources is an important statistical challenge, arising in many different fields. Combination is especially difficult when the sources are very diverse, requiring approaches beyond standard meta-analysis methods. The II-CC-FF paradigm (Independent Inspection, Confidence Conversion, Focused Fusion) is a general three-step method for such problems. The first step, II, uses different techniques to translate the information from each source to confidence distributions. Then these confidence distributions are transformed into confidence log-likelihoods in the CC-step, before being combined in the FF step. In this talk, the II-CC-FF scheme will be presented and illustrated by several non-standard and difficult applications. Demonstrating that II-CC-FF can be applied successfully both in traditional meta-analysis settings and in more challenging cases, where we need to combine classical experimental data (hard data) with less systematically collected information (soft data).


Authors who are presenting talks have a * after their name.

Back to the full JSM 2017 program

 
 
Copyright © American Statistical Association