Work

A note on detecting statistical outliers in psychophysical data

Year: 2019

Type: article

Abstract: This paper considers how best to identify statistical outliers in psychophysical datasets, where the underlying sampling distributions are unknown. Eight methods are described, and each is evaluated using Monte Carlo simulations of a typical psychophysical experiment. The best method is shown to be one based on a measure of absolute-deviation known as S n . This method is shown to be more accurate than popular heuristics based on standard deviations from the mean, and more robust than non-parametric methods based on interquartile range. Matlab code for computing S n is included.

Source: Attention Perception & Psychophysics

DOI: 10.3758/s13414-019-01726-3

Author: Pete R. Jones

Institutions: NIHR Moorfields Biomedical Research Centre, University College London

Language: English

Topic: Advanced Statistical Methods and Models

Subfield: Statistics and Probability

Field: Mathematics

Domain: Physical Sciences

Open Access status: hybrid

Estimated APC paid: $2,690

Funders: National Institute for Health and Care Research, Moorfields Eye Hospital NHS Foundation Trust