Statnote 4: what if the data are not normal?

Anthony Hilton, Richard A. Armstrong

Research output: Contribution to specialist publicationArticle

Abstract

When testing the difference between two groups, if previous data indicate non-normality, then either transform the data if they comprise percentages, integers or scores or use a non-parametric test. If there is uncertainty whether the data are normally distributed, then deviations from normality are likely to be small if the data are measurements to three significant figures. Unless there is clear evidence that the distribution is non-normal, it is more efficient to use the conventional t-tests. It is poor statistical practice to carry out both the parametric and non-parametric tests on a set of data and then choose the result that is most convenient to the investigator!
Original languageEnglish
Pages34-37
Number of pages4
Volume2006
Specialist publicationMicrobiologist
Publication statusPublished - Mar 2006

Fingerprint

Nonparametric test
Deviation
Normality
T-test
Non-normality
Integer
Uncertainty
Testing

Cite this

Hilton, Anthony ; Armstrong, Richard A. / Statnote 4: what if the data are not normal?. In: Microbiologist. 2006 ; Vol. 2006. pp. 34-37.
@misc{c43073ec24d04ba6bcb4b54232fd28b4,
title = "Statnote 4: what if the data are not normal?",
abstract = "When testing the difference between two groups, if previous data indicate non-normality, then either transform the data if they comprise percentages, integers or scores or use a non-parametric test. If there is uncertainty whether the data are normally distributed, then deviations from normality are likely to be small if the data are measurements to three significant figures. Unless there is clear evidence that the distribution is non-normal, it is more efficient to use the conventional t-tests. It is poor statistical practice to carry out both the parametric and non-parametric tests on a set of data and then choose the result that is most convenient to the investigator!",
author = "Anthony Hilton and Armstrong, {Richard A.}",
year = "2006",
month = "3",
language = "English",
volume = "2006",
pages = "34--37",
journal = "Microbiologist",
issn = "1479-2699",

}

Hilton, A & Armstrong, RA 2006, 'Statnote 4: what if the data are not normal?' Microbiologist, vol. 2006, pp. 34-37.

Statnote 4: what if the data are not normal? / Hilton, Anthony; Armstrong, Richard A.

In: Microbiologist, Vol. 2006, 03.2006, p. 34-37.

Research output: Contribution to specialist publicationArticle

TY - GEN

T1 - Statnote 4: what if the data are not normal?

AU - Hilton, Anthony

AU - Armstrong, Richard A.

PY - 2006/3

Y1 - 2006/3

N2 - When testing the difference between two groups, if previous data indicate non-normality, then either transform the data if they comprise percentages, integers or scores or use a non-parametric test. If there is uncertainty whether the data are normally distributed, then deviations from normality are likely to be small if the data are measurements to three significant figures. Unless there is clear evidence that the distribution is non-normal, it is more efficient to use the conventional t-tests. It is poor statistical practice to carry out both the parametric and non-parametric tests on a set of data and then choose the result that is most convenient to the investigator!

AB - When testing the difference between two groups, if previous data indicate non-normality, then either transform the data if they comprise percentages, integers or scores or use a non-parametric test. If there is uncertainty whether the data are normally distributed, then deviations from normality are likely to be small if the data are measurements to three significant figures. Unless there is clear evidence that the distribution is non-normal, it is more efficient to use the conventional t-tests. It is poor statistical practice to carry out both the parametric and non-parametric tests on a set of data and then choose the result that is most convenient to the investigator!

UR - http://issuu.com/societyforappliedmicrobiology/docs/micromarch06

M3 - Article

VL - 2006

SP - 34

EP - 37

JO - Microbiologist

JF - Microbiologist

SN - 1479-2699

ER -