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

Most procedures that have been proposed to identify dispersion effects in unreplicated factorial designs assume that location effects have been identified correctly. Incorrect identification of location effects may impair subsequent identification of dispersion effects. We develop a method for joint identification of location and dispersion effects that can reliably identify active effects of both types. A normal-based model containing parameters for effects in both the mean and variance is used. Parameters are estimated using maximum likelihood, and subsequent 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. Supplementary materials for this article are available online.

[1]  George M. Furnival,et al.  Regressions by leaps and bounds , 2000 .

[2]  C. F. Jeff Wu,et al.  Experiments: Planning, Analysis, and Parameter Design Optimization , 2000 .

[3]  A. Harvey.  Estimating Regression Models with Multiplicative Heteroscedasticity , 1976 .

[4]  Sabine Fenstermacher,et al.  Genetic Algorithms Data Structures Evolution Programs , 2016 .

[5]  Narayanaswamy Balakrishnan,et al.  ANALYZING UNREPLICATED FACTORIAL EXPERIMENTS: A REVIEW WITH SOME NEW PROPOSALS , 1998 .

[6]  B. Bergman,et al.  Dispersion effects from unreplicated designs in the 2 k-p series , 1997 .

[7]  P. C. Wang.  Tests for dispersion effects from orthogonal arrays , 1989 .

[8]  Yan Zhang.  A COMPARISON OF LOCATION EFFECT IDENTIFICATION METHODS FOR UNREPLICATED FRACTIONAL FACTORIALS IN THE PRESENCE OF DISPERSION EFFECTS , 2010 .

[9]  S. Weisberg,et al.  Diagnostics for heteroscedasticity in regression , 1983 .

[10]  Dennis K. J. Lin,et al.  Testing Multiple Dispersion Effects in Unreplicated Fractional Factorial Designs , 2001, Technometrics.

[11]  O. L. Davies,et al.  Design and analysis of industrial experiments , 1954 .

[12]  D. Ruppert,et al.  Transformation and Weighting in Regression , 1988 .

[13]  Nils Lid Hjort,et al.  Model Selection and Model Averaging , 2001 .

[14]  A. Ferrer,et al.  Small samples estimation of dispersion effects from unreplicated data , 1993 .

[15]  T. Loughin,et al.  An Adaptation of the Bergman–Hynén Test for Dispersion Effects in Unreplicated Two-Level Factorial Designs When the Location Model May Be Incorrect , 2013 .

[16]  J. Cavanaugh.  Unifying the derivations for the Akaike and corrected Akaike information criteria , 1997 .

[17]  George E. P. Box,et al.  Dispersion Effects From Fractional Designs , 1986 .

[18]  H. Akaike,et al.  Information Theory and an Extension of the Maximum Likelihood Principle , 1973 .

[19]  Zbigniew Michalewicz,et al.  Genetic Algorithms + Data Structures = Evolution Programs , 1996, Springer Berlin Heidelberg.

[20]  G. Pan.  The Impact of Unidentified Location Effects on Dispersion-Effects Identification From Unreplicated Factorial Designs , 1999, Technometrics.

[21]  Kenny Q. Ye,et al.  Critical Values of the Lenth Method for Unreplicated Factorial Designs , 2000 .

[22]  J. Engel,et al.  A generalized linear modeling approach to robust design , 1996 .

[23]  G. Kitagawa,et al.  Information Criteria and Statistical Modeling , 2007 .

[24]  Thomas M. Loughin,et al.  Computational issues with fitting joint location/dispersion models in unreplicated 2k factorials , 2011, Comput. Stat. Data Anal..

[25]  Sharla Gelfand.  Understanding the impact of heteroscedasticity on the predictive ability of modern regression methods , 2015 .

[26]  Zbigniew Michalewicz,et al.  Genetic Algorithms + Data Structures = Evolution Programs , 2000, Springer Berlin Heidelberg.

[27]  A Comparison of Location-Effect Identification Methods for Unreplicated Fractional Factorials in the Presence of Dispersion Effects , 2019 .

[28]  J. Grego,et al.  Quantile plots for mean effects in the presence of variance effects for 2k-p designs , 2000 .

[29]  Dennis K. J. Lin,et al.  Confounding of Location and Dispersion Effects in Unreplicated Fractional Factorials , 2001 .

[30]  R. Lenth.  Quick and easy analysis of unreplicated factorials , 1989 .

[31]  T. Loughin,et al.  A permutation test for effects in an unreplicated factorial design , 1997 .

[32]  D. Pregibon,et al.  Analyzing dispersion effects from replicated factorial experiments , 1988 .

[33]  Thomas M. Loughin,et al.  Calibration of the Length Test for Unreplicated Factorial Designs , 1998 .

[34]  Vijayan N. Nair,et al.  Methods for Identifying Dispersion Effects in Unreplicated Factorial Experiments , 2001, Technometrics.

[35]  David M. Steinberg,et al.  Screening Experiments for Dispersion Effects , 2006 .

[36]  John A. Nelder,et al.  Generalized linear models for the analysis of Taguchi-type experiments , 1991 .

[37]  David R. Anderson,et al.  Model selection and multimodel inference : a practical information-theoretic approach , 2003 .

[38]  B. Bergman,et al.  Dispersion Effects From 7 Unreplicated Designs in the 2 k—p Series , 1997 .

[39]  A. Raftery.  Bayesian Model Selection in Social Research , 1995 .

[40]  Richard N. McGrath.  Separating Location and Dispersion Effects in Unreplicated Fractional Factorial Designs , 2003 .

[41]  Nils Lid Hjort,et al.  Model Selection and Model Averaging: Contents , 2008 .

[42]  Clifford M. Hurvich,et al.  Regression and time series model selection in small samples , 1989 .

[43]  D. Montgomery.  USING FRACTIONAL FACTORIAL DESIGNS FOR ROBUST PROCESS DEVELOPMENT , 1990 .

[44]  G. Pan,et al.  On Generalized Linear Model Method for Detecting Dispersion Effects in Unreplicated Factorial Designs , 2002 .

[45]  Adrian E. Raftery,et al.  Bayesian model averaging: a tutorial (with comments by M. Clyde, David Draper and E. I. George, and a rejoinder by the authors , 1999 .