An empirical Bayes method for studying variation in knee replacement rates

Xiao Hua Zhou, Barry Katz, E. Holleman, C. A. Melfi, R. Dittus

Research output: Contribution to journalArticle

2 Citations (Scopus)

Abstract

Knee replacement is the most commonly used surgical treatment for knee arthritis. It has been reported that knee replacement rates vary across both regions and counties. This paper used data from Medicare patients to develop explanations for the variation. One problem with our data is that we do not have patient level information for Medicare patients who did not have a knee replacement during the study period. Therefore, even though our data have a natural hierarchical structure (region, county, patient), we cannot use a typical hierarchical model for the analysis due to missing patient level information. In this paper, we used a two-stage approach to analyse our data. In the first stage, we used an extra Poisson regression to model within-region variation of knee replacement rates while adjusting for the type of patient demographic information we had, and in the second stage, we used an empirical Bayes method to model between-region variation of knee replacement rates.

Original languageEnglish
Pages (from-to)1875-1884
Number of pages10
JournalStatistics in Medicine
Volume15
Issue number17-18
DOIs
StatePublished - Sep 15 1996

Fingerprint

Empirical Bayes Method
Replacement
Knee
Medicare
Arthritis
Poisson Regression
Hierarchical Model
Hierarchical Structure
Vary
Demography
Model

ASJC Scopus subject areas

  • Epidemiology

Cite this

An empirical Bayes method for studying variation in knee replacement rates. / Zhou, Xiao Hua; Katz, Barry; Holleman, E.; Melfi, C. A.; Dittus, R.

In: Statistics in Medicine, Vol. 15, No. 17-18, 15.09.1996, p. 1875-1884.

Research output: Contribution to journalArticle

Zhou, Xiao Hua ; Katz, Barry ; Holleman, E. ; Melfi, C. A. ; Dittus, R. / An empirical Bayes method for studying variation in knee replacement rates. In: Statistics in Medicine. 1996 ; Vol. 15, No. 17-18. pp. 1875-1884.
@article{d18224fa1e174aa289657df08c593087,
title = "An empirical Bayes method for studying variation in knee replacement rates",
abstract = "Knee replacement is the most commonly used surgical treatment for knee arthritis. It has been reported that knee replacement rates vary across both regions and counties. This paper used data from Medicare patients to develop explanations for the variation. One problem with our data is that we do not have patient level information for Medicare patients who did not have a knee replacement during the study period. Therefore, even though our data have a natural hierarchical structure (region, county, patient), we cannot use a typical hierarchical model for the analysis due to missing patient level information. In this paper, we used a two-stage approach to analyse our data. In the first stage, we used an extra Poisson regression to model within-region variation of knee replacement rates while adjusting for the type of patient demographic information we had, and in the second stage, we used an empirical Bayes method to model between-region variation of knee replacement rates.",
author = "Zhou, {Xiao Hua} and Barry Katz and E. Holleman and Melfi, {C. A.} and R. Dittus",
year = "1996",
month = "9",
day = "15",
doi = "10.1002/(SICI)1097-0258(19960915)15:17<1875::AID-SIM399>3.0.CO;2-4",
language = "English",
volume = "15",
pages = "1875--1884",
journal = "Statistics in Medicine",
issn = "0277-6715",
publisher = "John Wiley and Sons Ltd",
number = "17-18",

}

TY - JOUR

T1 - An empirical Bayes method for studying variation in knee replacement rates

AU - Zhou, Xiao Hua

AU - Katz, Barry

AU - Holleman, E.

AU - Melfi, C. A.

AU - Dittus, R.

PY - 1996/9/15

Y1 - 1996/9/15

N2 - Knee replacement is the most commonly used surgical treatment for knee arthritis. It has been reported that knee replacement rates vary across both regions and counties. This paper used data from Medicare patients to develop explanations for the variation. One problem with our data is that we do not have patient level information for Medicare patients who did not have a knee replacement during the study period. Therefore, even though our data have a natural hierarchical structure (region, county, patient), we cannot use a typical hierarchical model for the analysis due to missing patient level information. In this paper, we used a two-stage approach to analyse our data. In the first stage, we used an extra Poisson regression to model within-region variation of knee replacement rates while adjusting for the type of patient demographic information we had, and in the second stage, we used an empirical Bayes method to model between-region variation of knee replacement rates.

AB - Knee replacement is the most commonly used surgical treatment for knee arthritis. It has been reported that knee replacement rates vary across both regions and counties. This paper used data from Medicare patients to develop explanations for the variation. One problem with our data is that we do not have patient level information for Medicare patients who did not have a knee replacement during the study period. Therefore, even though our data have a natural hierarchical structure (region, county, patient), we cannot use a typical hierarchical model for the analysis due to missing patient level information. In this paper, we used a two-stage approach to analyse our data. In the first stage, we used an extra Poisson regression to model within-region variation of knee replacement rates while adjusting for the type of patient demographic information we had, and in the second stage, we used an empirical Bayes method to model between-region variation of knee replacement rates.

UR - http://www.scopus.com/inward/record.url?scp=0029793125&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0029793125&partnerID=8YFLogxK

U2 - 10.1002/(SICI)1097-0258(19960915)15:17<1875::AID-SIM399>3.0.CO;2-4

DO - 10.1002/(SICI)1097-0258(19960915)15:17<1875::AID-SIM399>3.0.CO;2-4

M3 - Article

C2 - 8888480

AN - SCOPUS:0029793125

VL - 15

SP - 1875

EP - 1884

JO - Statistics in Medicine

JF - Statistics in Medicine

SN - 0277-6715

IS - 17-18

ER -