Outlier Detection and Treatment in I/O Psychology: A Survey

Extreme data points, or outliers, can have a disproportionate influence on the conclusions drawn from a set of bivariate correlational data. Two aspects of outlier detection in industrial-organizational (I/O) psychology are addressed. The results of a survey regarding how published researchers prefe...

Full description

Saved in:
Bibliographic Details
Published inPersonnel psychology Vol. 44; no. 3; p. 473
Main Authors Orr, John M, Sackett, Paul R, Dubois, Cathy L Z
Format Journal Article
LanguageEnglish
Published Durham Blackwell Publishing Ltd 01.10.1991
Subjects
Personnel
Psychology
Statistical analysis
Statistical methods
Studies
Online AccessGet full text

Cover

More Information
Summary:Extreme data points, or outliers, can have a disproportionate influence on the conclusions drawn from a set of bivariate correlational data. Two aspects of outlier detection in industrial-organizational (I/O) psychology are addressed. The results of a survey regarding how published researchers prefer to deal with outliers are presented, and a set of 183 test validity studies is examined to document the effects of different approaches to the detection and exclusion of outliers on effect size measures. The analysis yields the following conclusions: 1. There is disagreement among researchers as to the appropriateness of deleting data points from a study. 2. Researchers report greater use of visual examination of data than of numeric diagnostic techniques for detecting outliers. 3. While outlier removal influenced effect size measures in individual studies, outlying data points were not found to be a substantial source of variance in a large test validity data set.
ISSN:0031-5826
1744-6570