ENBIS-16 in Sheffield

11 – 15 September 2016; Sheffield Abstract submission: 20 March – 4 July 2016

Prediction intervals under prior information

14 September 2016, 10:30 – 10:50

Abstract

Submitted by
Rainer Göb
Authors
Lennart Kann (Robert Bosch GmbH, Automotive Electronics), Rainer Göb (University of Würzburg)
Abstract
Prediction intervals are widely used in industry, in particular prediction intervals for the number of nonconforming units. For the latter purpose, various intervals have been suggested in the literature. However, these approaches are restricted in usefulness and applicability. In particular, none of these approaches accounts for prior information on the underlying proportion nonconforming p. In industrial environments, this type of prior information is always available, usually restricting attention to very small values of the proportion nonconforming p. We present shortest length intervals for the number of nonconforming units under prior information expressed by a beta distribution of the proportion nonconforming p.

Return to programme