Annals of Statistics

Sequential Bayes Estimation of the Difference Between Means

Thomas A. Kelley

Full-text: Open access

Abstract

It is desired to estimate the difference between the means of two independent normal distributions as accurately as possible and in a sequential manner when the total number of observations is fixed. The problem is posed in a Bayesian framework with conjugate prior distributions and squared error loss function. It is shown that the optimal sequential design depends on the ratio of the posterior variances of the two means. There exist constants (dependent on the prior parameters, the number of observations taken from each distribution, and the number of observations remaining) such that when the above-mentioned ratio exceeds this constant it is optimal to select the next observation from one distribution; otherwise it is optimal to select it from the other distribution.

Article information

Source
Ann. Statist., Volume 5, Number 2 (1977), 379-384.

Dates
First available in Project Euclid: 12 April 2007

Permanent link to this document
https://projecteuclid.org/euclid.aos/1176343803

Digital Object Identifier
doi:10.1214/aos/1176343803

Mathematical Reviews number (MathSciNet)
MR431552

Zentralblatt MATH identifier
0364.62029

JSTOR
links.jstor.org

Subjects
Primary: 62L12: Sequential estimation
Secondary: 93C40: Adaptive control

Keywords
Sequential estimation adaptive control process dynamic programming algorithm optimal strategy myopic rule

Citation

Kelley, Thomas A. Sequential Bayes Estimation of the Difference Between Means. Ann. Statist. 5 (1977), no. 2, 379--384. doi:10.1214/aos/1176343803. https://projecteuclid.org/euclid.aos/1176343803


Export citation