Exclusive Content & Downloads from ASQ

Alternative Prediction Intervals for Pareto Proportions

Summary: PLEASE NOTE: This article is identical to one of the same name published in the 51st Annual Quality Congress, QICID 10548. Do not order both.

The proportion of defects in a manufacturing or service-oriented process that are attributable o a specific root cause is often used to dictate maintenance actions. It is important to understand the underlying variability of this quality measure in order to avoid overreacting to fluctuations that are not unusual for the process when it is under control. We consider an approach where historical values of the proportion of defects for a given root cause are used to construct a prediction interval for a future value. If the historical data are assumed to be representative of the process when it is under control, the prediction interval can be used to identify future values that suggest a change in the root cause composition of defects. Three alternative prediction intervals are developed: a nonparametric interval; a bootstrap interval; and a parametric plug-in interval. The intervals are illustrated with a set of data pertaining to failures in the public telephone network. A simulation study is used to compare the three intervals with respect to coverage probability and expected length.

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.

Subscribe to Journal of Quality Technology

Access this and ALL OTHER Journal of Quality Technology online articles. You'll also receive the print version by mail.

  • Topics:
  • Keywords: Prediction intervals,Pareto charts,Bootstrap methods
  • Author: Jeske, Daniel R.; Marlow, Norman A.
  • Journal: Journal of Quality Technology