JSM 2012 Home

JSM 2012 Online Program

The views expressed here are those of the individual authors and not necessarily those of the JSM sponsors, their officers, or their staff.

Online Program Home

Abstract Details

Activity Number: 578
Type: Contributed
Date/Time: Wednesday, August 1, 2012 : 2:00 PM to 3:50 PM
Sponsor: Section on Bayesian Statistical Science
Abstract - #306835
Title: Model Selection Strategies Applied to Customer Research Data
Author(s): Jorge Alejandro*+
Companies: Market Probe
Address: 2655 N Mayfair Rd, Milwaukee, WI, 53226, United States
Keywords: Bayesian model selection ; Information criterion ; Customer research ; Multi-collinearity ; Multiple linear regression ; Quantile regression
Abstract:

Customer research focuses on modeling attitudinal outcomes that ultimately managers can act upon in order to influence the bottom line. Not surprisingly, a key element in this process is to be able to formulate what factors contribute to form customers' overall evaluations. However, oftentimes survey instruments are packed with a large number of attributes that even though could arguably be used to describe the customer experience, also pose a challenge due to the interrelatedness between them. Model selection can be seen as an alternative to dealing with a large number of attributes, with particular interest in the presence of multi-collinearity. In this presentation, common linear and nonlinear modeling techniques are applied to customer survey data while utilizing different model selection strategies including information-based and Bayesian regularization approaches. The results are compared in terms of model performance and the potential impact on managerial recommendation.


The address information is for the authors that have a + after their name.
Authors who are presenting talks have a * after their name.

Back to the full JSM 2012 program




2012 JSM Online Program Home

For information, contact jsm@amstat.org or phone (888) 231-3473.

If you have questions about the Continuing Education program, please contact the Education Department.