Oct 3, 10, 17, 24, 31, 2001
The use of Rating Scales and questionnaires
Many instruments for assessing various aspects of health are in
the form of questionnaires. Responses to the individual items are summed
with or without weighting to produce a score(s) for each subject. In this
workshop, we consider the structure and properties of such health status
indicators and the uses to which these instruments are most profitably
put.
A good overview of the kind of material to be covered is available in
McDowell and Newell (1996), who recognize seven dimensions that can be
used to characterize various aspects of health (or lack thereof):
(1) Physical disability and handicap
(2) Social Health
(3) Psychological well-being
(4) Depression
(5) Mental Status
(6) Pain
(7) General health status and quality of life
Most of the scales used to assess these dimensions of health consist of a
series of questions or statements to which the respondent provides an
answer or an ordinal rating. These are then combined to yield a score
indicating the amount or extent of handicap, depression, or pain.
Literally thousands of instruments of this kind have been developed. the
purpose of this workshop is to describe some of the uses to which such
instruments may be put, and to discuss some criteria that can be used in
evaluating and selecting among them. It will surprise no one that an
instrument which performs well in one setting may fail to do so in
another, but specific examples may help fix ideas, and some of the untoward
consequences of using the wrong tool for the job will be illustrated.
Instructors:
Chuck Kowalski is Faculty Associate at CSCAR and
Professor in the School of Dentistry at The
University of Michigan. He has extensive statistical
consulting experience in biomedical contexts,
including work with pharmaceutical companies, the
Nijmegen Growth Study, the Lancaster Cleft Palate
Clinic, the Veterans Administration Medical Center,
the National Football League, the Department of
Antiquities (Cairo), and (especially longitudinal)
data analysis, and has recently worked on pain
measurement, categorical data analysis, and
bioequivalence studies. Currently Chair of U-M's
Institutional Review Board II/Health, he also is
interested in research ethics, especially with
respect to study design and risk/benefit analysis.
Audience:
Anyone interested in modern methods for handing
non-response and missing data in statistical analysis. This workshop will
emphasize concepts and applications over technical details.
Prerequisite:
Familiarity with basic statistical concepts, including
probability distributions, estimations, maximum
likelihood and regression
Provisions:
Enrollees will receive lecture notes, and a
bibliography.
Date:
October 3, 10, 17, 24, 31, 2001.
Time:
3:00 p.m. - 5:00 p.m.
Location:
Room G 390 in the School of Dentistry, the University of
Michigan.
Fee:
$150 for University affiliated faculty, staff and
students; $300 for others. Fees can be paid by check
or billed to a University of Michigan Account.
Registration:
To register call CSCAR at 734-764-7828. If you are are
using a UM account please have the legacy account number
(short code) ready when calling to register. Please make
checks to CSCAR-University of Michigan and send to: CSCAR,
Suite 1210, Buhr Bldg., 837 Greene, 48104
|
