Generalized linear models for the analysis of taguchi‐type experiments
- 1 March 1991
- journal article
- research article
- Published by Wiley in Applied Stochastic Models and Data Analysis
- Vol. 7 (1) , 107-120
- https://doi.org/10.1002/asm.3150070110
Abstract
Recent interest in Taguchi's methods have led to developments in joint analysis of the mean and dispersion from designed experiments. A commonly used method is the analysis of variance of the transformed data. However, a single transformation cannot necessarily produce the Normality, constancy of variance and linearity of systematic effects for the mean and dispersion models. We describe the use of generalized linear models for the analysis of such experiments and illustrate the methods with a data set.Keywords
This publication has 27 references indexed in Scilit:
- Tests of Hypotheses in Overdispersed Poisson Regression and other Quasi-Likelihood ModelsJournal of the American Statistical Association, 1990
- Interpreting mean squares in saturated fractional designsJournal of Applied Statistics, 1989
- [Signal-to-Noise Ratios, Performance Criteria, and Transformations]: DiscussionTechnometrics, 1988
- [Signal-to-Noise Ratios, Performance Criteria, and Transformations]: DiscussionTechnometrics, 1988
- Variance Function EstimationJournal of the American Statistical Association, 1987
- Performance Measures Independent of Adjustment: An Explanation and Extension of Taguchi's Signal-to-Noise RatiosTechnometrics, 1987
- Modelling Variance Heterogeneity in Normal Regression Using GLIMJournal of the Royal Statistical Society Series C: Applied Statistics, 1987
- Dispersion Effects From Fractional DesignsTechnometrics, 1986
- Review: P. McCullagh, J. A. Nelder, Generalized Linear ModelsThe Annals of Statistics, 1984
- Use of Half-Normal Plots in Interpreting Factorial Two-Level ExperimentsTechnometrics, 1959