A Coefficient Alpha for Test-Retest Data

Samuel B. Green

Research output: Contribution to journalArticle

40 Citations (Scopus)

Abstract

Transient errors are caused by variations in feelings, moods, and mental states over time. If these errors are present, coefficient alpha is an inflated estimate of reliability. A true-score model is presented that incorporates transient errors for test-retest data, and a reliability estimate is derived. This estimate, referred to as the test-retest alpha, is less than coefficient alpha if transient error is present and is less susceptible to effects due to item recall than a test-retest correlation. An assumption underlying the test-retest alpha is essential tau equivalency of items. A test-retest split-half coefficient is presented as an alternative to the test-retest alpha when this assumption is violated. The test-retest alpha is the mean of all possible test-retest split-half coefficients.

Original languageEnglish (US)
Pages (from-to)88-101
Number of pages14
JournalPsychological Methods
Volume8
Issue number1
DOIs
StatePublished - Mar 2003

Fingerprint

Emotions

ASJC Scopus subject areas

  • Psychology(all)

Cite this

A Coefficient Alpha for Test-Retest Data. / Green, Samuel B.

In: Psychological Methods, Vol. 8, No. 1, 03.2003, p. 88-101.

Research output: Contribution to journalArticle

Green, Samuel B. / A Coefficient Alpha for Test-Retest Data. In: Psychological Methods. 2003 ; Vol. 8, No. 1. pp. 88-101.
@article{819121632f3945beb85297253546cbde,
title = "A Coefficient Alpha for Test-Retest Data",
abstract = "Transient errors are caused by variations in feelings, moods, and mental states over time. If these errors are present, coefficient alpha is an inflated estimate of reliability. A true-score model is presented that incorporates transient errors for test-retest data, and a reliability estimate is derived. This estimate, referred to as the test-retest alpha, is less than coefficient alpha if transient error is present and is less susceptible to effects due to item recall than a test-retest correlation. An assumption underlying the test-retest alpha is essential tau equivalency of items. A test-retest split-half coefficient is presented as an alternative to the test-retest alpha when this assumption is violated. The test-retest alpha is the mean of all possible test-retest split-half coefficients.",
author = "Green, {Samuel B.}",
year = "2003",
month = "3",
doi = "10.1037/1082-989X.8.1.88",
language = "English (US)",
volume = "8",
pages = "88--101",
journal = "Psychological Methods",
issn = "1082-989X",
publisher = "American Psychological Association Inc.",
number = "1",

}

TY - JOUR

T1 - A Coefficient Alpha for Test-Retest Data

AU - Green, Samuel B.

PY - 2003/3

Y1 - 2003/3

N2 - Transient errors are caused by variations in feelings, moods, and mental states over time. If these errors are present, coefficient alpha is an inflated estimate of reliability. A true-score model is presented that incorporates transient errors for test-retest data, and a reliability estimate is derived. This estimate, referred to as the test-retest alpha, is less than coefficient alpha if transient error is present and is less susceptible to effects due to item recall than a test-retest correlation. An assumption underlying the test-retest alpha is essential tau equivalency of items. A test-retest split-half coefficient is presented as an alternative to the test-retest alpha when this assumption is violated. The test-retest alpha is the mean of all possible test-retest split-half coefficients.

AB - Transient errors are caused by variations in feelings, moods, and mental states over time. If these errors are present, coefficient alpha is an inflated estimate of reliability. A true-score model is presented that incorporates transient errors for test-retest data, and a reliability estimate is derived. This estimate, referred to as the test-retest alpha, is less than coefficient alpha if transient error is present and is less susceptible to effects due to item recall than a test-retest correlation. An assumption underlying the test-retest alpha is essential tau equivalency of items. A test-retest split-half coefficient is presented as an alternative to the test-retest alpha when this assumption is violated. The test-retest alpha is the mean of all possible test-retest split-half coefficients.

UR - http://www.scopus.com/inward/record.url?scp=0043280893&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0043280893&partnerID=8YFLogxK

U2 - 10.1037/1082-989X.8.1.88

DO - 10.1037/1082-989X.8.1.88

M3 - Article

VL - 8

SP - 88

EP - 101

JO - Psychological Methods

JF - Psychological Methods

SN - 1082-989X

IS - 1

ER -