Online Program Home
My Program

Abstract Details

Activity Number: 288
Type: Invited
Date/Time: Tuesday, August 2, 2016 : 8:30 AM to 10:20 AM
Sponsor: Business and Economic Statistics Section
Abstract #318483
Title: Inherently High-dimensional Analysis with Indicator Saturation
Author(s): Neil R. Ericsson*
Companies: Federal Reserve Board
Keywords: Autometrics ; high-dimensional analysis ; impulse indicator saturation ; model selection ; robust estimation ; structural breaks
Abstract:

Indicator saturation is a generic approach to robust estimation, and to the detection and quantification of structural breaks. Saturation techniques are inherently high-dimensional and require automated model selection with non-standard inference. This paper characterizes several roles for saturation techniques and proposes extensions of impulse indicator saturation that have greater power to detect empirically common structural breaks. A model for the Brazilian inflation rate illustrates saturation techniques.


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

Back to the full JSM 2016 program

 
 
Copyright © American Statistical Association