Activity Number:
|
61
|
Type:
|
Invited
|
Date/Time:
|
Monday, August 12, 2002 : 8:30 AM to 10:20 AM
|
Sponsor:
|
Section on Health Policy Statistics*
|
Abstract - #300620 |
Title:
|
Bayesian and Non-Bayesian Methods and Applications in Provider Profiling
|
Author(s):
|
David Draper*+
|
Affiliation(s):
|
University of California, Santa Cruz
|
Address:
|
Baskin School of Engineering, 1156 High Street, Santa Cruz, California, 95064, USA
|
Keywords:
|
causal inference ; calibration ; fixed-effects hierarchical models ; league tables ; random-effects models ; standardization
|
Abstract:
|
Provider profiling is a potentially controversial approach to indirect quality assessment in (at least) the fields of health policy and education. In this talk, in joint work with Mark Gittoes, I will describe findings in two case studies involving profiling: an attempt to link indirect and direct quality assessments (based on explicit process measurement) in the Rand DRG Quality of Care study, and a method now in use by the UK government to measure the appropriateness of student dropout rates at British universities.
|