Abstract
| Language | English |
|---|---|
| Pages | 56-59 |
| Journal | Applied Psychological Measurement |
| Volume | 30 |
| Issue number | 1 |
| DOIs | |
| Publication status | Published - Jan 2006 |
Fingerprint
Cite this
}
Correcting coefficient alpha for correlated errors: Is alpha(K) a lower bound to reliability? / Rae, Gordon.
In: Applied Psychological Measurement, Vol. 30, No. 1, 01.2006, p. 56-59.Research output: Contribution to journal › Article
TY - JOUR
T1 - Correcting coefficient alpha for correlated errors: Is alpha(K) a lower bound to reliability?
AU - Rae, Gordon
PY - 2006/1
Y1 - 2006/1
N2 - When errors of measurement are positively correlated, coefficient alpha may overestimate the ``true'' reliability of a composite. To reduce this inflation bias, Komaroff (1997) has proposed an adjusted alpha coefficient, alpha(K). This article shows that alpha(K) is only guaranteed to be a lower bound to reliability if the latter does not include correlated error. If one's definition of reliability includes correlated error, then an alternative adjusted alpha, alpha(R), is suggested, which will always be a lower bound.
AB - When errors of measurement are positively correlated, coefficient alpha may overestimate the ``true'' reliability of a composite. To reduce this inflation bias, Komaroff (1997) has proposed an adjusted alpha coefficient, alpha(K). This article shows that alpha(K) is only guaranteed to be a lower bound to reliability if the latter does not include correlated error. If one's definition of reliability includes correlated error, then an alternative adjusted alpha, alpha(R), is suggested, which will always be a lower bound.
U2 - 10.1177/0146621605280355
DO - 10.1177/0146621605280355
M3 - Article
VL - 30
SP - 56
EP - 59
JO - Applied Psychological Measurement
T2 - Applied Psychological Measurement
JF - Applied Psychological Measurement
SN - 0146-6216
IS - 1
ER -