Statnote 1: is the data normal?

Abstract

Testing whether an observed distribution of observations deviates from normality is a common type of statistical test available in statistics software. Most software offer two ways of judging whether there are significant deviations of the observed from the expected distributions, viz., chi-square and the KS test. These tests have different sensitivities and problems and often give conflicting results. The results of these tests together with observations of the shape of the observed distribution should be used to judge normality.

Divisions: College of Health & Life Sciences > School of Biosciences
College of Health & Life Sciences > Chronic and Communicable Conditions
College of Health & Life Sciences
College of Health & Life Sciences > School of Optometry > Optometry
College of Health & Life Sciences > School of Optometry > Optometry & Vision Science Research Group (OVSRG)
College of Health & Life Sciences > School of Optometry > Vision, Hearing and Language
Uncontrolled Keywords: observed distribution,observations,normality,statistical test,statistics software,significant deviations
Publication ISSN: 1479-2699
Last Modified: 11 Nov 2024 09:10
Date Deposited: 19 Aug 2019 09:32
Full Text Link:
Related URLs: http://issuu.co ... ocs/microjune05 (Publisher URL)
PURE Output Type: Article
Published Date: 2005-06
Authors: Hilton, Anthony (ORCID Profile 0000-0001-8025-5270)
Armstrong, Richard A. (ORCID Profile 0000-0002-5046-3199)

Download

[img]

Version: Published Version

| Preview

Export / Share Citation


Statistics

Additional statistics for this record