Problems with interval estimates of the incremental cost-effectiveness ratio

Daniel F. Heitjan, Alan J. Moskowitz, William Whang

Research output: Contribution to journalArticle

36 Citations (Scopus)

Abstract

The defining feature of a confidence interval is that it has a fixed minimum probability of covering the true value of the parameter being estimated, whatever the value of the parameter. The authors demonstrate by simulation that some recently proposed methods for interval estimation of the incremental cost-effectiveness ratio (ICER) either do not satisfy this definition or have other problems that limit their usefulness in applications. The problems are most prominent when the ICER is large and the true effectiveness difference is small relative to its standard error. A modification of the percentile bootstrap confidence interval that involves a reordering of the sample space provides a partial solution of the problem.

Original languageEnglish (US)
Pages (from-to)9-15
Number of pages7
JournalMedical Decision Making
Volume19
Issue number1
DOIs
StatePublished - Jan 1 1999

Fingerprint

Cost-Benefit Analysis
Confidence Intervals

Keywords

  • Bootstrap
  • Clinical trials
  • Confidence intervals
  • Cost-effectiveness ratios
  • Fieller's method
  • Taylor series

ASJC Scopus subject areas

  • Health Policy

Cite this

Problems with interval estimates of the incremental cost-effectiveness ratio. / Heitjan, Daniel F.; Moskowitz, Alan J.; Whang, William.

In: Medical Decision Making, Vol. 19, No. 1, 01.01.1999, p. 9-15.

Research output: Contribution to journalArticle

Heitjan, Daniel F. ; Moskowitz, Alan J. ; Whang, William. / Problems with interval estimates of the incremental cost-effectiveness ratio. In: Medical Decision Making. 1999 ; Vol. 19, No. 1. pp. 9-15.
@article{932bfb3aab9e4a1c8bc361059ec0f236,
title = "Problems with interval estimates of the incremental cost-effectiveness ratio",
abstract = "The defining feature of a confidence interval is that it has a fixed minimum probability of covering the true value of the parameter being estimated, whatever the value of the parameter. The authors demonstrate by simulation that some recently proposed methods for interval estimation of the incremental cost-effectiveness ratio (ICER) either do not satisfy this definition or have other problems that limit their usefulness in applications. The problems are most prominent when the ICER is large and the true effectiveness difference is small relative to its standard error. A modification of the percentile bootstrap confidence interval that involves a reordering of the sample space provides a partial solution of the problem.",
keywords = "Bootstrap, Clinical trials, Confidence intervals, Cost-effectiveness ratios, Fieller's method, Taylor series",
author = "Heitjan, {Daniel F.} and Moskowitz, {Alan J.} and William Whang",
year = "1999",
month = "1",
day = "1",
doi = "10.1177/0272989X9901900102",
language = "English (US)",
volume = "19",
pages = "9--15",
journal = "Medical decision making : an international journal of the Society for Medical Decision Making",
issn = "0272-989X",
publisher = "SAGE Publications Inc.",
number = "1",

}

TY - JOUR

T1 - Problems with interval estimates of the incremental cost-effectiveness ratio

AU - Heitjan, Daniel F.

AU - Moskowitz, Alan J.

AU - Whang, William

PY - 1999/1/1

Y1 - 1999/1/1

N2 - The defining feature of a confidence interval is that it has a fixed minimum probability of covering the true value of the parameter being estimated, whatever the value of the parameter. The authors demonstrate by simulation that some recently proposed methods for interval estimation of the incremental cost-effectiveness ratio (ICER) either do not satisfy this definition or have other problems that limit their usefulness in applications. The problems are most prominent when the ICER is large and the true effectiveness difference is small relative to its standard error. A modification of the percentile bootstrap confidence interval that involves a reordering of the sample space provides a partial solution of the problem.

AB - The defining feature of a confidence interval is that it has a fixed minimum probability of covering the true value of the parameter being estimated, whatever the value of the parameter. The authors demonstrate by simulation that some recently proposed methods for interval estimation of the incremental cost-effectiveness ratio (ICER) either do not satisfy this definition or have other problems that limit their usefulness in applications. The problems are most prominent when the ICER is large and the true effectiveness difference is small relative to its standard error. A modification of the percentile bootstrap confidence interval that involves a reordering of the sample space provides a partial solution of the problem.

KW - Bootstrap

KW - Clinical trials

KW - Confidence intervals

KW - Cost-effectiveness ratios

KW - Fieller's method

KW - Taylor series

UR - http://www.scopus.com/inward/record.url?scp=0032894376&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0032894376&partnerID=8YFLogxK

U2 - 10.1177/0272989X9901900102

DO - 10.1177/0272989X9901900102

M3 - Article

C2 - 9917015

AN - SCOPUS:0032894376

VL - 19

SP - 9

EP - 15

JO - Medical decision making : an international journal of the Society for Medical Decision Making

JF - Medical decision making : an international journal of the Society for Medical Decision Making

SN - 0272-989X

IS - 1

ER -