Development of a censored robust design model for time‐oriented quality characteristics

Robust design (RD) techniques, which are based on the concept of building quality into products or processes, are increasingly popular in industry primarily because of their practicality. Traditional RD principles have often been applied to situations in which the quality characteristics of interest are time‐insensitive. However, when time‐oriented quality characteristics are studied, censored data often occur. As a result, current RD models reported in the literature may not be effective in finding solutions based on such data. To address such practical needs, this paper develops a censored RD model. We also propose an estimation method that is closely related to the expectation–maximization algorithm and compare it with the method of maximum likelihood estimation via a numerical example. Model validation is conducted, and comparative studies are discussed for model verification. Copyright © 2008 John Wiley & Sons, Ltd.