Cronbach's Alpha Values

Internal consistency

Cronbach's Alpha	Internal Consistency
0.9 ≤ α	Excellent
0.8 ≤ α < 0.9	Good
0.7 ≤ α < 0.8	Adequate
0.6 ≤ α < 0.7	Questionable

contributed by Frank LaBanca, EdD

See also 'Cronbachalpha.png'

Cronbach's alpha measures internal consistency, meaning how much the items on a scale actually measure the same dimension. For example, when considering instrumentation for quantitative research, part of assessing a reliable instrument would include reviewing the Cronbach's alpha values for the scales. An example of this is reported below, for the School Attitudes Assessment Survey - Revised (SAAS-R): As reported by McCoach and Siegle (2003), the scores demonstrated a classical theory internal consistency reliability coefficient of at least .85 on each of the five factors.

McCoach, D. B., & Siegle, D. (2003). The school attitude assessment survey – revised: A new instrument to identify academically able students who underachieve. Educational and Psychological Measurement, 63(3), 414-429. DOI: 10.1177/0013164402251057.

contributed by Lauren Moyer

Cronbach's Alpha is a measure of the correlations between all the variables that make up a scale. The concept behind this measure is to determine if items measure the same concept. If so, they will be highly correlated and have a high alpha, indicating a high level of internal consistency. However, the more items in a particular scale, the higher the alpha tends to be, even if the items don't measure the same thing. It is suggested that the researcher should also run a factor analysis to strengthen the reliability of the scale (Muijs, 2011).

contributed by Joseph W. Sullivan