Access the full text.
Sign up today, get DeepDyve free for 14 days.
Loading next page...
/lp/wiley/assessing-some-aspects-of-factor-screening-with-nonnormal-responses-A3yqEmwdPu
References (26)
-
J. Tyssedal, M. Chaudhry (2017)
The choice of screening designApplied Stochastic Models in Business and Industry, 33
-
A. Khuri, B. Mukherjee, B. Sinha, M. Ghosh (2006)
Design Issues for Generalized Linear Models: A ReviewStatistical Science, 21
-
J. Tyssedal, Shahrukh Hussain (2016)
Factor screening in nonregular two-level designs based on projection-based variable selectionJournal of Applied Statistics, 43
-
(1995)
A hidden projection property of Plackett‐Burman and related designs -
D. Woods, J. McGree, S. Lewis (2016)
Model selection via Bayesian information capacity designs for generalised linear modelsComput. Stat. Data Anal., 113
-
R. Plackett, J. Burman (1946)
THE DESIGN OF OPTIMUM MULTIFACTORIAL EXPERIMENTSBiometrika, 33
-
G. Box, J. Tyssedal (2001)
SIXTEEN RUN DESIGNS OF HIGH PROJECTIVITY FOR FACTOR SCREENINGCommunications in Statistics - Simulation and Computation, 30
-
GEP Box, J Tyssedal (2001)
Sixteen run designs of high projectivity for screening, 30
-
B. Jones, C. Nachtsheim (2011)
A Class of Three-Level Designs for Definitive Screening in the Presence of Second-Order EffectsJournal of Quality Technology, 43
-
D. Lin, N. Draper (1992)
Projection properties of Plackett and Burman designsTechnometrics, 34
-
Víctor Aguirre (2016)
Bayesian analysis of definitive screening designs when the response is nonnormalApplied Stochastic Models in Business and Industry, 32
-
Robert Mee (2009)
A Comprehensive Guide to Factorial Two-Level Experimentation -
Geroge Box, R. Meyer (1993)
Finding the Active Factors in Fractionated Screening ExperimentsJournal of Quality Technology, 25
-
S. Webb (1968)
Non-Orthogonal Designs of Even Resolution*Technometrics, 10
-
RH Myers, DC Montgomery, GG Vining (2002)
Generalized Linear Models With Applications in Engineering and the Sciences -
G. Box, J. Tyssedal (1996)
Projective properties of certain orthogonal arraysBiometrika, 83
-
V. Aguirre-Torres, Román Vara (2014)
A Bayesian Analysis of Very Small Unreplicated ExperimentsQuality and Reliability Engineering International, 30
-
J. Tyssedal, Hallgeir Grinde, C. Røstad (2006)
The Use of a 12‐run Plackett–Burman Design in the Injection Moulding of a Technical Plastic ComponentQuality and Reliability Engineering International, 22
-
Guan Yu (2009)
Variance stabilizing transformations of Poisson, binomial and negative binomial distributionsStatistics & Probability Letters, 79
-
Mark Wolters, D. Bingham (2011)
Simulated Annealing Model Search for Subset Selection in Screening ExperimentsTechnometrics, 53
-
B. Jones, C. Nachtsheim (2017)
Effective Design-Based Model Selection for Definitive Screening DesignsTechnometrics, 59
-
Sharon Lewis, D. Montgomery, R. Myers (2001)
Examples of Designed Experiments with Nonnormal ResponsesJournal of Quality Technology, 33
-
J. Tyssedal, Ranveig Niemi (2014)
Graphical Aids for the Analysis of Two-Level Nonregular DesignsJournal of Computational and Graphical Statistics, 23
-
S Hussain (2017)
Analysis and Exploration of Two‐Level Nonregular Designs by Using Projection Properties -
M. Freeman, J. Tukey (1950)
Transformations Related to the Angular and the Square RootAnnals of Mathematical Statistics, 21
-
AC Atkinson, DC Woods (2015)
Handbook of Design and Analysis of Experiments
- Publisher
- Wiley
- Copyright
- © 2019 John Wiley & Sons, Ltd.
- ISSN
- 1524-1904
- eISSN
- 1526-4025
- DOI
- 10.1002/asmb.2444
- Publisher site
- See Article on Publisher Site
Abstract
Nonnormally distributed response values, such as count data for instance, create challenges for factor screening. One problem is that variances may vary from run to run. Another is the choice of screening design for such responses. In this paper, we assess some screening performances for three popular screening designs: a definite screening design, a minimum resolution IV design, and a Plackett‐Burman design. Four distributions, two binomials, one gamma, and one Poisson are chosen for the response values. For each distribution, we test out if it is best to use the raw data, a variance‐stabilizing transformation of the data, or perform a generalized linear modeling assuming three factors are active. From our investigations, two‐level nonregular designs gave the highest success rate in identifying the subset of active factors and a variance‐stabilizing transformation turned out to perform equally good or better than generalized linear modeling in most cases.
Journal
Applied Stochastic Models in Business and Industry – Wiley
Published: Jul 1, 2019
Keywords: ; ;