Hypothesis Testing in Statistics

Roger L. Berger

Research output: Chapter in Book/Report/Conference proceedingChapter

1 Scopus citations

Abstract

A statistical hypothesis is a statement about one or more population parameter(s). A hypothesis test is a rule for deciding which of two complementary hypotheses is true, based on some data. Various methods for constructing hypothesis tests (e.g., likelihood, Bayesian, intersection-union) are available. Various measures for evaluating hypothesis tests, most of which are related to the tests' probabilities of making correct or incorrect decisions, are available, also. Construction and evaluation of tests, if a large sample is available, is sometimes simplified by asymptotic results.

Original languageEnglish (US)
Title of host publicationInternational Encyclopedia of the Social & Behavioral Sciences: Second Edition
PublisherElsevier Inc.
Pages491-493
Number of pages3
ISBN (Electronic)9780080970875
ISBN (Print)9780080970868
DOIs
StatePublished - Mar 26 2015
Externally publishedYes

Keywords

  • Acceptance region
  • Alternative hypothesis
  • Bayesian
  • Intersection-union
  • Level
  • Likelihood ratio
  • Null hypothesis
  • P-value
  • Power
  • Rejection region
  • Score test
  • Size
  • Type I error
  • Type II error
  • Union-intersection
  • Wald test

ASJC Scopus subject areas

  • Social Sciences(all)

Fingerprint

Dive into the research topics of 'Hypothesis Testing in Statistics'. Together they form a unique fingerprint.

Cite this