[gov3009-l] Sharon-Lise T. Normand: Wed/noon, Applied Stats Workshop

Alexis J. Diamond adiamond@fas.harvard.edu
Tue, 13 Apr 2004 00:17:17 -0400 (EDT)

Research Workshop in Applied Statistics
Join us this Wednesday (April 14) at noon,
at CBRSS, the Center for Basic Research in the Social Sciences,
34 Kirkland Street, Room 22,

Statistical Models for 
Health Care Quality Surveillance and Public Reporting

Sharon-Lise T. Normand
Professor of Health Care Policy (Biostatistics)
Department of Health Care Policy, Harvard Medical School
Department of Biostatistics, Harvard School of Public Health

Monitoring health care quality involves collection of medical data in 
order to identify trends and disparities in medical care delivery. In the 
absence of randomization, detailed medical record data have often served as the 
gold-standard for balancing the distribution of observations (e.g., 
patients) across units (e.g., states). Administrative claims data are a 
cheaper alternative to medical record data but have been criticized as too 
coarse. The question is how valid are the administrative data for 
monitoring health care quality. To answer this, we consider an analysis of 
I units, each of which involves an adjusted outcome. In the ith unit, we 
denote the true association between the outcome and the risk factors using 
the medical chart data by theta_i(X), the true association between the 
outcome and the risk factors using administrative data by gamma_i(Z), and 
assume we have estimates of each available. Within unit i, the estimated 
association parameters are jointly normally distributed such that 
conditional on gamma_i(Z), a simple linear relationship exists between 
theta_i(X) and gamma_i(Z). We illustrate methods to examine the value of 
administrative data for monitoring state-specific 30-day mortality rates 
after a heart attack. Preliminary results for monitoring hospital-specific
rates will also be discussed.

Key Words: Bayesian inference; hierarchical model; surrogacy; acute 
myocardial infarction; quality of care; surveillance.

As always, lunch will be provided.

Contact information, the current schedule, and previous presentations may be
found at the course web site: http://www.courses.fas.harvard.edu/~gov3009/


The Research Workshop in Applied Statistics is a forum for graduate
students, faculty, and visiting scholars to present and discuss work
in progress and exchange ideas.  It is intended as a tour of Harvard's
statistical innovations and applications with weekly stops in
different disciplines such as economics, epidemiology, medicine,
political science, psychology, public policy, public health, sociology
and statistics.  The topics of papers presented in previous years
included missing data, survey analysis, Bayesian simulation, sample
selection, and models for election and portfolio choice. Faculty and
student participants in the workshop present their current projects,
and guest speakers also give occasional presentations. The workshop
provides an excellent opportunity for informal interaction between
graduate students and faculty from a variety of disciplines. Course
credit is available for students as either an upper-level Government
or Sociology class. Lunch is provided.

If you are interested, note that all events are held at noon, in Room 22,
Center for Basic Research in Social Sciences (CBRSS, 34 Kirkland St., this is
the yellow building across the street from William James Hall).
Contact information and previous presentations may be found at the course web
site: http://www.courses.fas.harvard.edu/~gov3009/

To join the gov3009 mailing list, send e-mail to
gov3009-l-request@fas.harvard.edu with the following text message: