No abstract

In Taguchi's parameter design, the significant parameter levels are found by maximising the signal-to-noise ratio of the quality characteristic. In the analysis of variance (ANOVA) of signal-to-noise ratio, the combination of column effects to better estimate error variance is referred to as pooling. Taguchi has suggested the strategy of pooling up. When using the pooling-up strategy, there will be a tendency to make the alpha mistake more often. In this paper, it is assumed that (1) the quality chartacteristic is normally distributed and (2) the mean and standard deviation of each factor level combination are equal, then the null hypothesis should be no significant factor. Thus, the alpha risk is that some factors are misidentified as significant factors. The purpose of this paper is to investigate the alpha risk of the Taguchi method for the-larger-the-better (LTB) type problem with orthogonal array, L 8 , by simulation. The results show that the alpha risk is very high.