Exclusive Content & Downloads from ASQ

Rejoinder of "“Recent Advances in Process Monitoring: Nonparametric and Variable-Selection Methods for Phase I and Phase II”

Summary: This article is a response to two commentaries on an article by Giovanna Capizzi, “Recent Advances in Process Monitoring: Nonparametric and Variable-Selection Methods for Phase I and Phase II,” Quality Engineering, Volume 27, Number 1 (January 2015), pages 44-67. The two commentaries, by Wolfgang Schmid and Emmanuel Yashchin, appear elsewhere (on pages 68-72 and 73-76, respectively) in the same issue. Capizzi notes that the emphasis on a nonparametric approach to Phase I needs to be interpreted as strictly connected to an incomplete knowledge on the underlying process. On the other hand, she believes that the use of parametric techniques, possibly based on flexible distribution families, should be strongly encouraged in Phase II when a reference sample from a stable process has been obtained and standard goodness-of-fit t tests can be correctly applied and interpreted. Fitting some appropriate distribution to process readings requires some time, expertise, and the skill of adapting suitable parametric statistical tools to the fitted distribution. Conversely, the key idea of nonparametric methods is to provide an easy way to check whether the process is in conformance without the mathematical and computational complexity of choosing a parametric distribution for an unknown (possibly unstable) process. Regarding Phase II, she observes that least absolute shrinkage and selection operator (LASSO) and forward search (FS) algorithms can be viewed as two extremes: the LASSO uses shrunk estimates while FS uses unshrunk estimates; experiments show that unshrunken estimators outperform shrunken estimators for most SPM applications.

Anyone with a subscription, including Site and Enterprise members, can access this article.

Other Ways to Access content:

Join ASQ

Join ASQ as a Full member. Enjoy all the ASQ member benefits including access to many online articles.

  • Topics: Statistical Process Control (SPC)
  • Keywords: Monitoring, Nonparametric methods, Control charts, Multivariate control charts, Distribution-free procedures, Statistical process control (SPC), Shewhart control chart, Variable selection
  • Author: Capizzi, Giovanna;
  • Journal: Quality Engineering