Elsevier

Information Processing Letters

Volume 49, Issue 3, 11 February 1994, Pages 129-133
Information Processing Letters

An algorithm to estimate the fraction defective and the exponential mean life using unlabeled samples

https://doi.org/10.1016/0020-0190(94)90089-2Get rights and content

Abstract

A method is presented to estimate the percentages and the exponential mean lifetimes of products from two manufacturing processes using a mixture of unlabeled samples. The results of a Monte Carlo study are presented to demonstrate the accuracy of the estimation method. All estimates will converge to the true unknown parameters (percentages and mean lifetimes) when the size of the unlabeled sample increases.

References (9)

  • R.L. Kasyap et al.

    Stochastic approximation

  • D. Kazakos

    Recursive estimation of prior probabilities using a mixture

    IEEE Trans. Inform. Theory

    (1977)
  • U.E. Makov et al.

    A quasi-Bayes unsupervised learning procedure for priors

    IEEE Trans. Inform. Theory

    (1977)
  • R. Mizoguchi et al.

    An approach to unsupervised learning classification

    IEEE Trans. Comput.

    (1975)
There are more references available in the full text version of this article.

Cited by (0)

View full text
Copyright © 1994 Published by Elsevier B.V.