Joint Identification of Location and Dispersion Effects in Unreplicated Two-Level Factorials

Peer reviewed: 
Yes, item is peer reviewed.
Scholarly level: 
Faculty/Staff
Final version published as: 

Final version will be published in Technometrics (http://www.tandfonline.com/loi/utch20) and will appear in revised form.

Date created: 
2015-10
Keywords: 
Maximum likelihood
Corrected heteroscedastic information criterion
Model averaging
Exhaustive search
ESMA-CHIC
Abstract: 

Most procedures that have been proposed to identify dispersion effects in unreplicated factorial designs assume that location effects have been identified correctly. Incorrect identi- fication of location effects may impair subsequent identification of dispersion effects. We develop a model for joint identification of location and dispersion effects that can reliably identify active effects of both types. The joint model is estimated using maximum likelihood, and hence effect selection is done using a specially derived information criterion. An exhaustive search through a limited version of the space of possible models is conducted. Both a single-model output and model averaging are considered. The method is shown to be capable of identifying sensible location-dispersion models that are missed by methods that rely on sequential estimation of location and dispersion effects.

Language: 
English
Document type: 
Article
Rights: 
You are free to copy, distribute and transmit this work under the following conditions: You must give attribution to the work (but not in any way that suggests that the author endorses you or your use of the work); You may not use this work for commercial purposes; You may not alter, transform, or build upon this work. Any further uses require the permission of the rights holder (or author if no rights holder is listed). These rights are based on the Creative Commons Attribution-NonCommercial-NoDerivatives License.
Sponsor(s): 
Natural Sciences and Engineering Research Council of Canada (NSERC)
Statistics: