Skip to Main Content
Nonparametric Bayesian predictive distributions for future order statisticsAuthor(s): Richard A. Johnson; James W. Evans; David W. Green
Source: Statistics & probability letters. Vol. 41, no. 3 (Feb. 1999). :p. 247-254.
Publication Series: Miscellaneous Publication
PDF: Download Publication (105 KB)
DescriptionWe derive the predictive distribution for a specified order statistic, determined from a future random sample, under a Dirichlet process prior. Two variants of the approach are treated and some limiting cases studied. A practical application to monitoring the strength of lumber is discussed including choices of prior expectation and comparisons made to a Bayesian parametric approach.
- We recommend that you also print this page and attach it to the printout of the article, to retain the full citation information.
- This article was written and prepared by U.S. Government employees on official time, and is therefore in the public domain.
CitationJohnson, Richard A.; Evans, James W.; Green, David W. 1999. Nonparametric Bayesian predictive distributions for future order statistics. Statistics & probability letters. Vol. 41, no. 3 (Feb. 1999). :p. 247-254.
KeywordsWood strength, Statistics, Distribution, Prediction, Bayesian theory, Monitoring
- Predictor sort sampling and one-sided confidence bounds on quantiles
- VIEWIT uses on the wild and scenic upper Missouri River
- Strategies for selecting and breeding EAB-resistant ash
XML: View XML