Methods for estimating and interpreting provider-specific standardized mortality ratios

Jiannong Liu, Thomas Louis, Wei Pan, Jennie Z. Ma, Allan J. Collins

Research output: Contribution to journalArticle

Abstract

Standardized Mortality Ratios (SMRs) are widely used as a measurement of quality of care for profiling and otherwise comparing medical care providers. Invalid estimation or inappropriate interpretation may have serious local and national consequences. Estimating an SMR entails producing provider-specific expected deaths via a statistical model and then computing the "observed/expected" ratio. Appropriate comparison of estimated SMRs requires considering both estimated values and statistical uncertainty. With statistical uncertainty that varies over providers, hypothesis testing to identify poor performers unfairly penalizes large providers; use of direct estimates unfairly penalizes small providers. Since neither approach suffices, we report on a suite of comparisons, each addressing an important aspect of the comparison. Our approach is based on a hierarchical statistical model. Goals include estimating and ranking (percentiling) provider-specific SMRs and calculating the probability that a provider's true SMR percentile falls within a specified percentile range. We present the issues and related statistical models for comparing SMRs and apply our approaches to the 1998 United States Renal Data System (USRDS) dialysis provider data.

Original languageEnglish (US)
Pages (from-to)135-149
Number of pages15
JournalHealth Services and Outcomes Research Methodology
Volume4
Issue number3
DOIs
StatePublished - Sep 2003

Fingerprint

Mortality
Statistical Models
Uncertainty
Quality of Health Care
Information Systems
Dialysis
Kidney

Keywords

  • Bayesian hierarchical models
  • End-Stage Renal Disease (ESRD)
  • Percentile estimates
  • Standardized Mortality Ratio (SMR)
  • United States Renal Data System (USRDS)

ASJC Scopus subject areas

  • Health Policy
  • Public Health, Environmental and Occupational Health

Cite this

Methods for estimating and interpreting provider-specific standardized mortality ratios. / Liu, Jiannong; Louis, Thomas; Pan, Wei; Ma, Jennie Z.; Collins, Allan J.

In: Health Services and Outcomes Research Methodology, Vol. 4, No. 3, 09.2003, p. 135-149.

Research output: Contribution to journalArticle

Liu, Jiannong ; Louis, Thomas ; Pan, Wei ; Ma, Jennie Z. ; Collins, Allan J. / Methods for estimating and interpreting provider-specific standardized mortality ratios. In: Health Services and Outcomes Research Methodology. 2003 ; Vol. 4, No. 3. pp. 135-149.
@article{4a6f7744158b4a259ef3bb5f89b67a81,
title = "Methods for estimating and interpreting provider-specific standardized mortality ratios",
abstract = "Standardized Mortality Ratios (SMRs) are widely used as a measurement of quality of care for profiling and otherwise comparing medical care providers. Invalid estimation or inappropriate interpretation may have serious local and national consequences. Estimating an SMR entails producing provider-specific expected deaths via a statistical model and then computing the {"}observed/expected{"} ratio. Appropriate comparison of estimated SMRs requires considering both estimated values and statistical uncertainty. With statistical uncertainty that varies over providers, hypothesis testing to identify poor performers unfairly penalizes large providers; use of direct estimates unfairly penalizes small providers. Since neither approach suffices, we report on a suite of comparisons, each addressing an important aspect of the comparison. Our approach is based on a hierarchical statistical model. Goals include estimating and ranking (percentiling) provider-specific SMRs and calculating the probability that a provider's true SMR percentile falls within a specified percentile range. We present the issues and related statistical models for comparing SMRs and apply our approaches to the 1998 United States Renal Data System (USRDS) dialysis provider data.",
keywords = "Bayesian hierarchical models, End-Stage Renal Disease (ESRD), Percentile estimates, Standardized Mortality Ratio (SMR), United States Renal Data System (USRDS)",
author = "Jiannong Liu and Thomas Louis and Wei Pan and Ma, {Jennie Z.} and Collins, {Allan J.}",
year = "2003",
month = "9",
doi = "10.1023/B:HSOR.0000031400.77979.b6",
language = "English (US)",
volume = "4",
pages = "135--149",
journal = "Health Services and Outcomes Research Methodology",
issn = "1387-3741",
publisher = "Springer Netherlands",
number = "3",

}

TY - JOUR

T1 - Methods for estimating and interpreting provider-specific standardized mortality ratios

AU - Liu, Jiannong

AU - Louis, Thomas

AU - Pan, Wei

AU - Ma, Jennie Z.

AU - Collins, Allan J.

PY - 2003/9

Y1 - 2003/9

N2 - Standardized Mortality Ratios (SMRs) are widely used as a measurement of quality of care for profiling and otherwise comparing medical care providers. Invalid estimation or inappropriate interpretation may have serious local and national consequences. Estimating an SMR entails producing provider-specific expected deaths via a statistical model and then computing the "observed/expected" ratio. Appropriate comparison of estimated SMRs requires considering both estimated values and statistical uncertainty. With statistical uncertainty that varies over providers, hypothesis testing to identify poor performers unfairly penalizes large providers; use of direct estimates unfairly penalizes small providers. Since neither approach suffices, we report on a suite of comparisons, each addressing an important aspect of the comparison. Our approach is based on a hierarchical statistical model. Goals include estimating and ranking (percentiling) provider-specific SMRs and calculating the probability that a provider's true SMR percentile falls within a specified percentile range. We present the issues and related statistical models for comparing SMRs and apply our approaches to the 1998 United States Renal Data System (USRDS) dialysis provider data.

AB - Standardized Mortality Ratios (SMRs) are widely used as a measurement of quality of care for profiling and otherwise comparing medical care providers. Invalid estimation or inappropriate interpretation may have serious local and national consequences. Estimating an SMR entails producing provider-specific expected deaths via a statistical model and then computing the "observed/expected" ratio. Appropriate comparison of estimated SMRs requires considering both estimated values and statistical uncertainty. With statistical uncertainty that varies over providers, hypothesis testing to identify poor performers unfairly penalizes large providers; use of direct estimates unfairly penalizes small providers. Since neither approach suffices, we report on a suite of comparisons, each addressing an important aspect of the comparison. Our approach is based on a hierarchical statistical model. Goals include estimating and ranking (percentiling) provider-specific SMRs and calculating the probability that a provider's true SMR percentile falls within a specified percentile range. We present the issues and related statistical models for comparing SMRs and apply our approaches to the 1998 United States Renal Data System (USRDS) dialysis provider data.

KW - Bayesian hierarchical models

KW - End-Stage Renal Disease (ESRD)

KW - Percentile estimates

KW - Standardized Mortality Ratio (SMR)

KW - United States Renal Data System (USRDS)

UR - http://www.scopus.com/inward/record.url?scp=4344598373&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=4344598373&partnerID=8YFLogxK

U2 - 10.1023/B:HSOR.0000031400.77979.b6

DO - 10.1023/B:HSOR.0000031400.77979.b6

M3 - Article

C2 - 19606272

AN - SCOPUS:4344598373

VL - 4

SP - 135

EP - 149

JO - Health Services and Outcomes Research Methodology

JF - Health Services and Outcomes Research Methodology

SN - 1387-3741

IS - 3

ER -