Research on Reliability and Comparative Inference.

Abstract

Francisco J. Samaniego, Distinguished Research Professor of Statistics at the University of California, Davis, has had continuous research support from the Army Research Office from 1999 Ð 2016. The present proposal to the ARO seeks support for one year, via a STTR, grant for the purpose of continuing Dr. SamaniegoÕs research work in three specific problem areas. (1) Investigations are proposed aimed at identifying uniformly optimal communication networks with respect to the stochastic precedence ordering. The proposal reviews recent work extending the findings in McAssey and Samaniego (2014) and proposes to develop further extensions as well as to investigate the connection between optimal network reliability and the Òdegree distributionsÓ of all networks of a given size, i.e., with a fixed number of vertices and edges; (2) The estimation of component reliability based on system failure-time data will be investigated using nonparametric Bayesian methods; (3) A collection of open problems in comparative statistical inference will be investigated. Specifically, the comparison of the Bayesian and frequentist approaches to the testing of statistical hypotheses will be undertaken. Motivated by the results of a large simulation study based on published data from Òthe word-length experimentÓ, Dr. Samaniego and his colleagues will focus on the development of a mathematical framework from which definitive results may be obtained regarding the circumstances in which Bayes tests are superior (or conversely, inferior) to classical (frequentist) tests such as Neyman-Pearson or likelihood ratio tests. Samaniego (2010) has dealt successfully with comparative inference for point estimators, a fact that lends credibility to the feasibility of the proposed project.

Document Details

Document Type
DoD Grant Award
Publication Date
Oct 11, 2018
Source ID
W911NF1710381

Entities

People

  • Francisco Samaniego

Organizations

  • Army Contracting Command
  • United States Army
  • University of California, Davis

Tags

Readers

  • Research Science/Academic Research
  • Statistical inference.
  • Theoretical Analysis.

Technology Areas

  • AI & ML
  • AI & ML - Bayesian Inference
  • AI & ML - Machine Learning Algorithms