00275 v5f3b08f35004cd682f15c427cbecd4

277

Some Guidelines for Designing an Industrial Expcriment

experiment, but we learn the answers as we go along. This argues in favor of the iterative or seąuential approach discussed previously. Of course, there are situations where comprehensive experiments are entirely appropriate, but as a generał rule, most experiments should be iterative. Conseąuently, this is why we advocate the 25 percent rule: never invest morę than about 25 percent of the resources of experimentation (runs, budget, time, etc.) in the initial design. Often these first efforts are just learning experiences, and some resources must be available to accomplish the finał objectives of the experiment.

References

Bishop, T., Petersen, B., and Trayser, D. (1982), "Another Look at the Statistician's Role in Experimental Planning and Design," The American Statistician, 36, 387-389.

Box, G. E. P., Hunter, W. G., and Hunter, J. S. (1978), Statistics for Experimenters, New York, John Wiley.

Coleman, D. E. and Montgomery, D. C. (1993), "A Systematic Approach to Planning for a Designed Industrial Experiment" (with discussion), Technometrics, 35, 1-27.

Hahn, G. (1977), “Some Things Engineers Should Know About Experimental Design," Journal of Quality Technology, 9, 13-20.

Hahn, G. (1984), "Experimental Design in a Complex World," Technometrics, 26, 19-31.

Hoadley, A., and Kettenring, J. (1990), "Communications Between Statisticians and Engineers/Physical Scientists" (with commentary), Technometrics, 32, 243-274.

Montgomeiy, D. C. (1991), Design and Analysis of Experiments (3rd ed.) New York, John Wiley.

Montgomery, D. C. and Runger, G. C. (1993a), "Gauge Capability Analysis and Designed Experiments, Part I: Basic Methods," Quality Engineering, 6, 115-135.