As the question is on rating scales, perhaps you would be interested to
visit another avenue as well.
Rasch analysis is an emerging, and intuitively rewarding statistical method
for analysis and development of rating scales, based on item response
theory. It provides measures, rather than counts what raw scores of rating
scales basically are, and models both items and persons who respond to them
on an equal logit scale. I became familiar with this method a few years ago
and have found that it greatly broadened my horizons in this particular
field.
The Rasch analysis provides an additional means, common person equating, to
address the question whether two tests address one dimension, and that the
same dimension is addressed by both tests. This method, and other basics of
Rasch analysis, are described in the very readable book: Bond & Fox.
Applying the Rasch model. Lawrence Erlbaum, 2001. Common person equating is
described in chapter 5, "Test equating: can two tests measure the same
ability?".
In particular, I have found that Bland-Altman on raw scores and common
person equating of Rasch measurements, based on the same raw scores, may no=
t
always result in the same interpretation, and I am tempted to believe that
those from the Rasch analysis are more meaningful.
Stata has capabilities in Rasch analysis through ado files, but at the
moment dedicated programs are more user friendly (I am familiar only with
Winsteps, but there are several other as well; I do look forward to more
Rasch ados from statalisters who have programming skills).
Tero Kivel=E4
-----Alkuper=E4inen viesti-----
L=E4hett=E4j=E4: [email protected]
[mailto:[email protected]] Puolesta Hom, Willard
L=E4hetetty: 7. joulukuuta 2005 0:08
Vastaanottaja: '[email protected]'
Aihe: st: uses of Bland-Altman plots
Anyone,
I'm wondering if anyone knows if it is appropriate to use the Bland-Altman
approach (as implemented
in STATA) for comparing the measurements from two separate rating
mechanisms. That is, I'm checking
whether two rating sytems that rate the same population of objects can be
"tested" for their
equivalence through the Bland-Altman method (plots, etc.).
In my perusal of literature that mentions use of the Bland-Altman method, I
have only seen its
application in the comparison of two measurement devices that measure
'physical qualities" (as in
medical/health research). Has anyone seen an application (and a defensible
one) of the method in
psychology, sociology, or economics, where there may be an interest in
exploring the equivalence of
two sets of ratings of the same objects/persons/constructs....
Thanks for any advice,
Willard Hom
*
* For searches and help try:
* http://www.stata.com/support/faqs/res/findit.html
* http://www.stata.com/support/statalist/faq
* http://www.ats.ucla.edu/stat/stata/
*
* For searches and help try:
* http://www.stata.com/support/faqs/res/findit.html
* http://www.stata.com/support/statalist/faq
* http://www.ats.ucla.edu/stat/stata/
