Estimating physician costliness: An empirical bayes approach

Michael E. Miller, Siu L. Hui, William M. Tierney, Clement J. McDonald

Research output: Contribution to journalArticle

15 Citations (Scopus)

Abstract

Outpatient data obtained from the general medicine practice of an urban, health care facility are used to provide an application of empirical Bayes techniques in the estimation of physician “costliness.” The results illustrate that application of the simplest empirical Bayes estimation procedure can provide more reasonable estimates of physician’s utilization of resources than a standard estimation procedure. Empirical Bayes estimates are shown to adjust for potential instability in standard estimates that may arise from either a physician treating a small number of patients or an inappropriate case-mix adjustment. Using simulation, it is demonstrated that the empirical Bayes procedure can provide overall better estimates using fewer data than the standard procedure. This application, although somewhat limited in scope, should provide impetus for increased utilization of the numerous Bayesian and empirical Bayes techniques that currently exist in the statistical literature and pertain to small area estimation techniques.

Original languageEnglish (US)
Pages (from-to)YS16-YS28
JournalMedical care
Volume31
Issue number5
StatePublished - May 1993

Fingerprint

estimation procedure
physician
Physicians
utilization
general medicine
Urban Health
Risk Adjustment
Health Facilities
General Practice
health care
simulation
Outpatients
Medicine
Delivery of Health Care
resources

ASJC Scopus subject areas

  • Public Health, Environmental and Occupational Health

Cite this

Miller, M. E., Hui, S. L., Tierney, W. M., & McDonald, C. J. (1993). Estimating physician costliness: An empirical bayes approach. Medical care, 31(5), YS16-YS28.

Estimating physician costliness : An empirical bayes approach. / Miller, Michael E.; Hui, Siu L.; Tierney, William M.; McDonald, Clement J.

In: Medical care, Vol. 31, No. 5, 05.1993, p. YS16-YS28.

Research output: Contribution to journalArticle

Miller, ME, Hui, SL, Tierney, WM & McDonald, CJ 1993, 'Estimating physician costliness: An empirical bayes approach', Medical care, vol. 31, no. 5, pp. YS16-YS28.
Miller ME, Hui SL, Tierney WM, McDonald CJ. Estimating physician costliness: An empirical bayes approach. Medical care. 1993 May;31(5):YS16-YS28.
Miller, Michael E. ; Hui, Siu L. ; Tierney, William M. ; McDonald, Clement J. / Estimating physician costliness : An empirical bayes approach. In: Medical care. 1993 ; Vol. 31, No. 5. pp. YS16-YS28.
@article{3c5c9fff8c104775a2cdca3c33987d52,
title = "Estimating physician costliness: An empirical bayes approach",
abstract = "Outpatient data obtained from the general medicine practice of an urban, health care facility are used to provide an application of empirical Bayes techniques in the estimation of physician “costliness.” The results illustrate that application of the simplest empirical Bayes estimation procedure can provide more reasonable estimates of physician’s utilization of resources than a standard estimation procedure. Empirical Bayes estimates are shown to adjust for potential instability in standard estimates that may arise from either a physician treating a small number of patients or an inappropriate case-mix adjustment. Using simulation, it is demonstrated that the empirical Bayes procedure can provide overall better estimates using fewer data than the standard procedure. This application, although somewhat limited in scope, should provide impetus for increased utilization of the numerous Bayesian and empirical Bayes techniques that currently exist in the statistical literature and pertain to small area estimation techniques.",
author = "Miller, {Michael E.} and Hui, {Siu L.} and Tierney, {William M.} and McDonald, {Clement J.}",
year = "1993",
month = "5",
language = "English (US)",
volume = "31",
pages = "YS16--YS28",
journal = "Medical Care",
issn = "0025-7079",
publisher = "Lippincott Williams and Wilkins",
number = "5",

}

TY - JOUR

T1 - Estimating physician costliness

T2 - An empirical bayes approach

AU - Miller, Michael E.

AU - Hui, Siu L.

AU - Tierney, William M.

AU - McDonald, Clement J.

PY - 1993/5

Y1 - 1993/5

N2 - Outpatient data obtained from the general medicine practice of an urban, health care facility are used to provide an application of empirical Bayes techniques in the estimation of physician “costliness.” The results illustrate that application of the simplest empirical Bayes estimation procedure can provide more reasonable estimates of physician’s utilization of resources than a standard estimation procedure. Empirical Bayes estimates are shown to adjust for potential instability in standard estimates that may arise from either a physician treating a small number of patients or an inappropriate case-mix adjustment. Using simulation, it is demonstrated that the empirical Bayes procedure can provide overall better estimates using fewer data than the standard procedure. This application, although somewhat limited in scope, should provide impetus for increased utilization of the numerous Bayesian and empirical Bayes techniques that currently exist in the statistical literature and pertain to small area estimation techniques.

AB - Outpatient data obtained from the general medicine practice of an urban, health care facility are used to provide an application of empirical Bayes techniques in the estimation of physician “costliness.” The results illustrate that application of the simplest empirical Bayes estimation procedure can provide more reasonable estimates of physician’s utilization of resources than a standard estimation procedure. Empirical Bayes estimates are shown to adjust for potential instability in standard estimates that may arise from either a physician treating a small number of patients or an inappropriate case-mix adjustment. Using simulation, it is demonstrated that the empirical Bayes procedure can provide overall better estimates using fewer data than the standard procedure. This application, although somewhat limited in scope, should provide impetus for increased utilization of the numerous Bayesian and empirical Bayes techniques that currently exist in the statistical literature and pertain to small area estimation techniques.

UR - http://www.scopus.com/inward/record.url?scp=0027598868&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0027598868&partnerID=8YFLogxK

M3 - Article

C2 - 8492581

AN - SCOPUS:0027598868

VL - 31

SP - YS16-YS28

JO - Medical Care

JF - Medical Care

SN - 0025-7079

IS - 5

ER -