Examining group differences in reliability of multi-component measuring
instruments
A talk by
Tenko Raykov
Fordham University
in Seminar Room 1
Institute of Psychiatry
Decrespigny Park
London SE5 8AF
outside attendees please email
[log in to unmask]
Thursday 14th June 2001 at 2.30pm
A covariance structure modelling method for examining group differences in
scale reliability of multi-component measuring instruments is proposed.
The procedure is based on a set of appropriate parameter constraints
imposed in a multiple-population structural model. Unlike tests of group
differences in coefficient alpha that in general do not evaluate the
discrepancies in scale reliability coefficients, the described approach
permits one to examine differences in the latter quantities of actual
interest when concerned with questions pertaining to reliability of
composite scores. The method can be used to test whether (i) a given
measuring instrument has identical reliabilities in studied populations;
and/or (ii) distinct instruments, or modes of administration of the same
instrument, have equal reliabilities across groups. The proposed
procedure is related to recent ones for addressing problems in reliability
estimation, scale construction and development, and is illustrated with a
pair of examples.
*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-
Regards,
Harriet Meteyard
Room S213, Department of Biostatistics & Computing,
Institute of Psychiatry, De Crespigny Park,
Denmark Hill, London, SE5 8AF, UK.
*PLEASE NOTE NEW TELEPHONE AND FAX NUMBERS*
(phone) +44 (0) 20-7848 0304 (fax) +44 (0) 20 -7848 0281
(email alias) [log in to unmask]
*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-
|