Detection of interactions in experiments on large numbers of factors

One of the main advantages of factorial experiments is the information that they can offer on interactions. When there are many factors to be studied, some or all of this information is often sacrificed to keep the size of an experiment economically feasible. Two strategies for group screening are presented for a large number of factors, over two stages of experimentation, with particular emphasis on the detection of interactions. One approach estimates only main effects at the first stage (classical group screening), whereas the other new method (interaction group screening) estimates both main effects and key two‐factor interactions at the first stage. Three criteria are used to guide the choice of screening technique, and also the size of the groups of factors for study in the first‐stage experiment. The criteria seek to minimize the expected total number of observations in the experiment, the probability that the size of the experiment exceeds a prespecified target and the proportion of active individual factorial effects which are not detected. To implement these criteria, results are derived on the relationship between the grouped and individual factorial effects, and the probability distributions of the numbers of grouped factors whose main effects or interactions are declared active at the first stage. Examples are used to illustrate the methodology, and some issues and open questions for the practical implementation of the results are discussed.

[1]  A. Sterrett.  On the Detection of Defective Members of Large Populations , 1957 .

[2]  G. Watson.  A Study of the Group Screening Method , 1961 .

[3]  Chou Hsiung Li.  A Sequential Method for Screening Experimental Variables , 1962 .

[4]  R. N. Gurnow.  A Note on G. S. Watson's Paper ‘A Study of the Group Screening Method” , 1965 .

[5]  PETER J. CAMERON,et al.  Embedding Edge-Colored Complete Graphs in Binary Affine Spaces , 1976, J. Comb. Theory, Ser. A.

[6]  J. Richmond.  A General Method for Constructing Simultaneous Confidence Intervals , 1982 .

[7]  T. J. Mitchell,et al.  Two-Level Multifactor Designs for Detecting the Presence of Interactions , 1983 .

[8]  M. S Patel,et al.  Two-stage group-screening designs with unequal a-prior probabilities , 1984 .

[9]  C. A. Mauro.  On the Performance of Two-Stage Group Screening Experiments , 1984 .

[10]  R. N. Kackar.  Off-Line Quality Control, Parameter Design, and the Taguchi Method , 1985 .

[11]  Jw Odhiambo,et al.  On multistage group screening designs , 1986 .

[12]  R. Daniel Meyer,et al.  An Analysis for Unreplicated Fractional Factorials , 1986 .

[13]  Jack P. C. Kleijnen,et al.  Review of random and group-screening designs , 1987 .

[14]  Max D. Morris,et al.  Two-stage factor screening procedures using multiple grouping assignments , 1987 .

[15]  Jerome Sacks,et al.  Computer Experiments for Quality Control by Parameter Design , 1990 .

[16]  P. McCullagh,et al.  Generalized Linear Models, 2nd Edn. , 1990 .

[17]  Kwok-Leung Tsui,et al.  Economical experimentation methods for robust design , 1991 .

[18]  Accelerated weathering of marine fabrics , 1992 .

[19]  Dennis K. J. Lin.  A new class of supersaturated designs , 1993 .

[20]  Search designs for estimating main effects and searching several two-factor interactions in general factorials , 1993 .

[21]  Changbao Wu,et al.  Construction of supersaturated designs through partially aliased interactions , 1993 .

[22]  Jiahua Chen,et al.  A catalogue of two-level and three-level fractional factorial designs with small runs , 1993 .

[23]  Susan M. Lewis,et al.  Response Surface Methodology and Taguchi: A Quality Improvement Study from the Milling Industry , 1993 .

[24]  W. DuMouchel,et al.  A simple Bayesian modification of D-optimal designs to reduce dependence on an assumed model , 1994 .

[25]  Dennis K. J. Lin.  Generating Systematic Supersaturated Designs , 1995 .

[26]  J. Hsu.  Multiple Comparisons: Theory and Methods , 1996 .

[27]  David C. Torney,et al.  Optimal Pooling Designs with Error Detection , 1994, J. Comb. Theory, Ser. A.

[28]  Søren Bisgaard,et al.  Designing experiments for tolerancing assembled products , 1997 .

[29]  Arden Miller.  Strip-plot configurations of fractional factorials , 1997 .

[30]  James M. Lucas,et al.  Designs of mixed resolution for process robustness studies , 1997 .

[31]  H. Chipman,et al.  A Bayesian variable-selection approach for analyzing designed experiments with complex aliasing , 1997 .

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

[33]  Andrew P Morris,et al.  Pooling DNA in the identification of parents , 1998, Heredity.

[34]  C McCollin,et al.  The future role of statistics in quality engineering and management , 1999 .

[35]  K. Vijayan,et al.  Some Risks in the Construction and Analysis of Supersaturated Designs , 1999, Technometrics.

[36]  Rahul Mukerjee,et al.  On a property of probability matching priors: matching the alternative coverage probabilities , 1999 .

[37]  Robert W. Mee,et al.  Fractional factorial designs that restrict the number of treatment combinations for factor subsets , 2000 .

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

[39]  William Li,et al.  Model-Robust Factorial Designs , 2000, Technometrics.

[40]  Changbao Wu,et al.  FACTOR SCREENING AND RESPONSE SURFACE EXPLORATION , 2001 .

[41]  Susan M. Lewis,et al.  Experiments for derived factors with application to hydraulic gear pumps , 2001 .

[42]  P. Rowley,et al.  On Generating and Classifying All Q N-M Regular Designs for Square-Free Q , 2001 .

[43]  Angela M. Dean,et al.  Comparison of group screening strategies for factorial experiments , 2002 .