Keywords: fractional design, Taguchi design, two-level design, dispersion effects.
The data set comprises the results of a saturated 215-11 fractional factorial with 4 observations per run. There were 15 controllable factors. The responses are the proportional shrinkage of four samples taken from 3000-foot lengths of speedometer cable manufactured at each set of conditions. The objective was to reduce the post-extrusion shrinkage of the speedometer casing.
|D||liner line speed|
|E||wire braid type|
|K||coating die type|
|y1||shrinkage value of first sample|
|y2||shrinkage value of second sample|
|y3||shrinkage value of third sample|
|y4||shrinkage value of fourth sample|
Note: the data actually give columns for -L, -J, -I, -E, -C and -O as in Box (1988).
Data File (tab-delimited text)
|Quinlan, J. (1985). Production improvement by application of Taguchi methods. Amer. Supplier Inst. News, special symposium edition, 11-16.|
|Box, G. E. P. (1988). Signal-to-noise ratios, performance criteria and transformations. Technometrics 30, 1-17.|
|Nelder, J. A., and Lee, Y. (1991). Generalized linear models for the analysis of Taguchi-type experiments. Applied Stochastic Models and Data Analysis 7, 107-120.|
|Lee, Y., and Nelder, J. A. (1998). Generalized linear models for the analysis of quality-improvement experiments. Canadian Journal of Statistics 26, 95-105.|