The Annals of Statistics

Bounds on Mixtures of Distributions Arising in Order Restricted Inference

Tim Robertson and F. T. Wright

Full-text: Open access

Abstract

In testing hypotheses involving order restrictions on a collection of parameters, distributions arise which are mixtures of standard distributions. Since tractable expressions for the mixing proportions generally do not exist even for parameter collections of moderate size, the implementation of these tests may be difficult. Stochastic upper and lower bounds are obtained for such test statistics in a variety of these kinds of problems. These bounds are also shown to be tight. The tightness results point out some situations in which the bounds could be used to obtain approximate methods. These results can also be applied to obtain the least favorable configuration when testing the equality of two multinomial populations versus a stochastic ordering alternative.

Article information

Source
Ann. Statist., Volume 10, Number 1 (1982), 302-306.

Dates
First available in Project Euclid: 12 April 2007

Permanent link to this document
https://projecteuclid.org/euclid.aos/1176345713

Digital Object Identifier
doi:10.1214/aos/1176345713

Mathematical Reviews number (MathSciNet)
MR642742

Zentralblatt MATH identifier
0481.62016

JSTOR
links.jstor.org

Subjects
Primary: 62E15: Exact distribution theory
Secondary: 62G10: Hypothesis testing

Keywords
Order restricted inference tests for and against a trend Chi-bar-squared distribution $E$-bar-squared distribution tail probability bounds least favorable configurations

Citation

Robertson, Tim; Wright, F. T. Bounds on Mixtures of Distributions Arising in Order Restricted Inference. Ann. Statist. 10 (1982), no. 1, 302--306. doi:10.1214/aos/1176345713. https://projecteuclid.org/euclid.aos/1176345713


Export citation