Since the early 1980s, industry has embraced the use of designed exper
iments as an effective means for improving quality. For quality charac
teristics not normally distributed, the practice of first transforming
the data and then analyzing them by standard normal-based methods is
well established. There is a natural alternative called generalized li
near models (GLMs). This paper explains how GLMs achieve the intended
goal of transformation while at the same time giving a wider class of
models that can handle a range of applications. Moreover, the same ite
rative strategy for data analysis that has been developed for normal d
ata over the years, namely, the alternation between model selection an
d model checking, extends easily to analyses with GLMs. The paper illu
strates the ability of GLMs to handle many different types of data by
the re-analysis of three quality-improvement experiments.