Facial reconstruction

Search LJMU Research Online

Browse Repository | Browse E-Theses

Advice on testing the null hypothesis that a sample is drawn from a Normal distribution.

Ruxton, GD, Wilkinson, DM and Neuhauser, M (2015) Advice on testing the null hypothesis that a sample is drawn from a Normal distribution. Animal Behaviour, 107. pp. 249-252. ISSN 0003-3472

[img] Text
markus normality testing (finalised).pdf - Accepted Version
Available under License Creative Commons Attribution Non-commercial No Derivatives.

Download (704kB)


The Normal distribution remains the most widely-used statistical model, so it is only natural that researchers will frequently be required to consider whether a sample of data appears to have been drawn from a Normal distribution. Commonly-used statistical packages offer a range of alternative formal statistical tests of the null hypothesis of Normality, with inference being drawn on the basis of a calculated p-value. Here we aim to review the statistical literature on the performance of these tests, and briefly survey current usage of them in recently-published papers, with a view to offering advice on good practice. We find that authors in animal behaviour seem to be using such testing most commonly in situations where it is inadvisable (or at best unnecessary) involving pre-testing to select parametric or not-parametric analyses; and making little use of it in model-fitting situations where it might be of value. Of the many alternative tests, we recommend the routine use of either the Shapiro-Wilk or Chen-Shapiro tests; these are almost always superior to commonly-used alternatives like the Kolmogorov-Smirnov test, often by a substantial margin. We describe how both our recommend tests can be implemented. In contrast to current practice as indicated by our survey, we recommend that the results of these tests are reported in more detail (providing both the calculated sample statistic and the associated p-value). Finally, emphasize that even the higher-performing tests of Normality have low power (generally below 0.5 and often much lower) when sample sizes are less than 50, as is often the case in our field.

Keywords: Gaussian distribution, parametric statistics, Schapiro-Wilk test, statistics, statistical power

Item Type: Article
Uncontrolled Keywords: 06 Biological Sciences, 07 Agricultural And Veterinary Sciences, 17 Psychology And Cognitive Sciences
Subjects: Q Science > QH Natural history > QH301 Biology
Divisions: Natural Sciences & Psychology (closed 31 Aug 19)
Publisher: Elsevier
Date Deposited: 13 Jul 2015 13:26
Last Modified: 09 Mar 2022 08:50
DOI or Identification number: 10.1016/j.anbehav.2015.07.006
URI: https://researchonline.ljmu.ac.uk/id/eprint/1570

Actions (login required)

View Item View Item