A Comparison of Two Sampling Schemes when Testing a Simple Hypothesis versus a Simple Alternative.

Abstract

A large deviation result is established for sequences of random variables with random indices. This result is used to compare two different sampling schemes when testing for a simple hypothesis versus a simple alternative. It turns out that the sampling scheme yielding more expected number of observations for the same sampling cost is not necessarily the more profitable procedure. Properties other than the mean of the distribution of the occurrence of the observations play a role in determining the more profitable sampling rule. (Author)

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Aug 01, 1977
Accession Number
ADA052811

Entities

People

  • James Lynch
  • Jayaram Sethuraman

Organizations

  • Florida State University

Tags

Communities of Interest

  • Biomedical
  • C4I

DTIC Thesaurus Topics

  • Computations
  • Efficiency
  • Inequalities
  • Military Research
  • New York
  • Normal Distribution
  • Observation
  • Probability
  • Random Variables
  • Sampling
  • Sequences
  • Statistical Tests
  • Statistics
  • Theorems
  • United States

Fields of Study

  • Mathematics

Readers

  • Economics
  • Statistical inference.