Nonparametric Bayesian predictive distributions for future order statistics

Richard A. Johnson; James W. Evans; David W. Green

Treesearch

Nonparametric Bayesian predictive distributions for future order statistics

Informally Refereed

Authors:

Richard A. Johnson, James W. Evans, David W. Green

Year:

1999

Type:

Miscellaneous Publication

Station:

Forest Products Laboratory

Source:

Statistics & probability letters. Vol. 41, no. 3 (Feb. 1999). :p. 247-254.

Download (PDF 108 KB)

Download (PDF 108 KB): https://research.fs.usda.gov/download/treesearch/5799.pdf

Abstract

We 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.

Keywords

Wood strength, Statistics, Distribution, Prediction, Bayesian theory, Monitoring

Citation

Johnson, 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.