Original article
Estimating the reliability of continuous measures with cronbach's alpha or the intraclass correlation coefficient: Toward the integration of two traditions

https://doi.org/10.1016/0895-4356(91)90076-LGet rights and content

Abstract

The epidemiological literature has been ambiguous concerning reliability estimates for continuous variables. Reproducibility and internal consistency have been presented as different aspects of reliability, the former being estimated with some form of intraclass correlation coefficient, the latter with Cronbach's alpha. Based on demonstrations available in the literature this paper recalls that both estimates are based on the same measurement model and on the same definition of reliability. It also highlights the conditions under which they are equivalent and provides practical suggestions concerning the estimation of reliability, based on design considerations.

References (39)

  • G. Guyatt et al.

    Measuring change over time: assessing the usefulness of evaluative instruments

    J Chron Dis

    (1987)
  • B. Kirshner et al.

    A methodological framework for assessing health indices

    J Chron Dis

    (1985)
  • E.G. Carmines et al.

    Reliability and Validity Assessment

    (1979)
  • J.C. Nunnally

    Psychometric Theory

    (1978)
  • M.J. Allen et al.

    Introduction to Measurement Theory

    (1979)
  • G.W. Bohrnstedt

    Measurement

  • F.M. Lord et al.

    Statistical Theories of Mental Test Scores

    (1968)
  • J.L. Fleiss

    The Design and Analysis of Clinical Experiments

    (1985)
  • K. Liu

    Measurement error and its impact on partial correlation and multiple linear regression analysis

    Am J Epidemiol

    (1988)
  • L.L. Kupper

    Effects of the use of unreliable surrogate variables on the validity of epidemiological research studies

    Am J Epidemiol

    (1984)
  • S. Greenland

    The effect of misclassification in the presence of covariates

    Am J Epidemiol

    (1980)
  • G.F. Kuder et al.

    The theory of the estimation of test reliability

    Psychometrika

    (1937)
  • L.J. Cronbach

    Coefficient alpha and the internal structure of a test

    Psychometrika

    (1951)
  • R.A. Fisher

    On the “probable error” of a coefficient of correlation deduced from a small sample

    Metron

    (1921)
  • A.R. Feinstein

    Clinimetrics

    (1987)
  • K.G. Joreskog

    A general approach to confirmatory maximum likelihood factor analysis

    Psychometrika

    (1969)
  • R.K. Hambleton et al.

    Item Response Theory

    (1985)
  • L. Guttman

    Reliability formulas that do not assume experimental independence

    Psychometrika

    (1953)
  • M.R. Novick et al.

    Coefficient alpha and the reliability of composite measurements

    Psychometrika

    (1967)
  • Cited by (267)

    • Sex-specific associations of early postnatal blood copper levels with neurodevelopment at 2 years of age

      2022, Journal of Trace Elements in Medicine and Biology
      Citation Excerpt :

      A special clinic was set up in the study hospital for the neurodevelopment tests of the children, and the tests were performed by two professional pediatricians. Internal consistency has been presented as an aspect of reliability, estimated using Cronbach's alpha coefficient [4]. The cut-off values for the Cronbach's alpha values were classified as: unacceptable (<0.7), acceptable (0.7–0.8), good (0.8–0.9), and excellent (>0.9) [9,41].

    View all citing articles on Scopus
    View full text