Being Inconsistent About Consistency: When Coefficient Alpha Does and Doesn't Matter

By D. Streiner. Journal of Personality Assessment, 2003

925 citations recorded by the source corpus.

Subfields: Experimental and Cognitive Psychology, Management Science and Operations Research, Social Psychology

View Paper: https://www.semanticscholar.org/paper/69fcecdd92fb0f984876c4cf58e6f4653852667a

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Experimental and Cognitive Psychology

In Management Science and Operations Research

In Social Psychology

Citations in the corpus

Metodología de investigación y lectura crítica de estudios Aproximación al uso del coeficiente alfa (2005, background): “mensionales, no en escalas multidimensionales (3,20,21,33).”
Reductions in Long-Term Suspensions Following Adoption of the Virginia Student Threat Assessment Guidelines (2011, background): “These levels of internal consistency suggest that the knowledge scores were not homogeneous measures of a single construct but could be considered acceptable as an index of a more complex construct (Streiner, 2003).”
Treating Cronbach’s Alpha Reliability Coefficients as Data in Counseling Research (2006, methodology): “A source of confusion is that some measurement experts advise interpreting internal consistency reliability coefficients, such as alpha, as evidence of scale-score unidimensionality or homogeneity if they are large enough (e.g., Nunnally, 1970; Streiner, 2003a).”
The COSMIN checklist for evaluating the methodological quality of studies on measurement properties: A clarification of its content (2010, background): “These items are called effect indicators and are expected to be highly correlated and interchangeable [9].”
Development and validation of the Current Opioid Misuse Measure (2007, methodology): “While there is some disagreement on what constitutes acceptable levels of internal consistency parameters (e.g., Nunnally and Bernstein, 1994; Streiner, 2003a,b; Butler, 2004), we adopted the convention of acceptable coefficient as as being between .70 and .80, as suggested by others developing…”
The impact of voluntary disclosure on cost of equity capital estimates in a temporal setting (2007, background): “Category III posed a problem with an alpha of only 0.232, indicating a potential invalidity in this category.”
A Comparison of Self and Peer Reports in the Assessment of Middle School Bullying (2009, background): “This alpha was not high enough to indicate that teacher tolerance is a homogenous construct but is considered acceptable for more complex constructs that assess conceptually related behaviors or attitudes, and might be regarded as an index rather than a scale (Streiner, 2003).”
Interpretaciones del Coeficiente Alpha de Cronbach (2005, background): “…evidencia de la calidad de una prueba, índice de validez de medidas psicológicas, estimador de confiabilidad interobservadores, entre otros (Webster, 1957; Green, Lissitz & Mulaik, 1977; Cortina, 1993; Bernardi, 1994; Peterson, 1994; Iacobucci, 2001; Schmidt et al., 2003; Streiner, 2003).”
Assessment of Sleep Hygiene Using the Sleep Hygiene Index (2006, methodology): “…items thought to have a causal impact on the variable being measured (causal items) necessitates a different set of assumptions and design processes than is typical in classical test theory (Bollen and Lennox, 1991; Diamantopoulos and Winklhofer, 2001; MacCallum and Browne, 1993; Streiner, 2003).”
Quality criteria were proposed for measurement properties of health status questionnaires. (2007, neutral): “In contrast, for questionnaires in which the items are merely different aspects of a complex clinical phenomenon that do not have to be correlated, such as in the Apgar Scale [20], internal consistency is not relevant [21,22].”
Coolness: An Empirical Investigation (2012, background): “Other theoretically-developed constructs may be composed of rela- Journal of Individual Differences 2012; Vol. 33(3):175–185 © 2012 Hogrefe Publishing tively distinct independent components (Streiner, 2003).”
Daily Dynamics of Personal Identity and Self–Concept Clarity (2011, background): “Ensuring that a scale generates valid and reliable scores is a necessary prerequisite to using this scale to test theory (Streiner, 2003).”
Age differences in instability, contingency, and level of self-esteem across the life span (2011, neutral): “dicators (see Bollen & Lennox, 1991; Streiner, 2003).”
The Good Judge Revisited: Individual Differences in the Accuracy of Personality Judgments (2005, background): “Although the internal consistency estimate of this composite was .60, it can be argued that this is more of an index than a scale (cf. Streiner, 2003).”
A Communicative Interdependence Perspective of Close Relationships: The Connections Between Mediated and Unmediated Interactions Matter (2013, methodology): “Unlike scales, the items in an index are causal indicators of a construct and, as such, are not necessarily assumed to correlate with one another (see Bollen & Lennox, 1991; Streiner, 2003).”