Identification of Dispersion Effects in Replicated Two-Level Fractional Factorial Experiments
- 1 Downloads
Tests for dispersion effects in replicated two-level factorial experiments assuming a location-dispersion model are presented. The tests use individual measures of dispersion that remove the location effects and also provide an estimate of pure error. Empirical critical values for two such tests are given for two-level full or regular fractional factorial designs with 8, 16, 32, and 64 runs. The powers of the tests are examined under normal, exponential, and Cauchy distributed errors. Our recommended test uses dispersion measures calculated as deviations of the data values from their cell medians, and this test is illustrated via an example.
KeywordsDispersion measures Location-dispersion model Fractional factorial experiment
Unable to display preview. Download preview PDF.
- Ankenman, B. E., and A. M. Dean. 2003. Quality improvement and robustness via design of experiments. In Handbook of statistics, ed. C. R. Rao, and R. Khattree, vol. 22, 263–317. Amsterdam, The Netherlands, Elsevier.Google Scholar
- Dingus, C. A. V. 2005. Designs and methods for the identification of active location and dispersion effects. Ph.D. thesis, The Ohio State University, Columbus, OH.Google Scholar
- Levene, H. 1960. Robust tests for equality of variances. In Contributions to probability and statistics: Essays in honor of Harold Hotelling, ed. I. Olkin, S. G. Ghurye, W. Hoeffding, W. G. Madow, and H. B. Mann, Stanford, CA, Stanford University Press.Google Scholar
- Mackertich, N. A., J. C. Benneyan, and P. D. Kraus. 2003. Alternate dispersion measures in replicated factorial experiments. Unpublished manuscript. http://www1.coe.neu.edu/∼benneyan/papers/doe_dispersion.pdf
- Montgomery, D. C. 2009. Design and analysis of experiments. 7th ed. New York, NY, John Wiley & Sons.Google Scholar
- Pignatiello, J. J., and J. S. Ramberg. 1987. Comments on “Performance Measures Independent of Adjustment: An Explanation and Extension of Taguchi’s Signal-to-noise Ratios.” Technometrics, 29, 274–277.Google Scholar