A comparison of approaches to estimating confidence intervals for willingness to pay measures

A.R. Hole

A comparison of approaches to estimating confidence intervals for willingness to pay measures

A.R. Hole

Centre for Health Economics

Research output: Book/Report › Commissioned report

Abstract

This paper describes three approaches to estimating confidence intervals for willingness to pay measures, the delta, Krinsky and Robb and bootstrap methods. The accuracy of the various methods is compared using a number of simulated datasets. In the majority of the scenarios considered all three methods are found to be reasonably accurate as well as yielding similar results. The delta method is the most accurate when the data is well-conditioned, while the bootstrap is more robust to noisy data and misspecification of the model. These conclusions are illustrated by empirical data from a study of willingness to pay for a reduction in waiting time for a general practitioner appointment in which all the methods produce fairly similar confidence intervals.

Original language	English
Place of Publication	York, UK
Publisher	Centre for Health Economics, University of York
Number of pages	28
Publication status	Published - Jan 2006

Publication series

Name	CHE Research Paper
Publisher	Centre for Health Economics

Bibliographical note

Keywords

willingness to pay
confidence interval
delta method
boot-strap

Access to Document

Cite this

@book{c0a43ea2a2794c62be436ead61334192,

title = "A comparison of approaches to estimating confidence intervals for willingness to pay measures",

abstract = "This paper describes three approaches to estimating confidence intervals for willingness to pay measures, the delta, Krinsky and Robb and bootstrap methods. The accuracy of the various methods is compared using a number of simulated datasets. In the majority of the scenarios considered all three methods are found to be reasonably accurate as well as yielding similar results. The delta method is the most accurate when the data is well-conditioned, while the bootstrap is more robust to noisy data and misspecification of the model. These conclusions are illustrated by empirical data from a study of willingness to pay for a reduction in waiting time for a general practitioner appointment in which all the methods produce fairly similar confidence intervals.",

keywords = "willingness to pay, confidence interval, delta method, boot-strap",

author = "A.R. Hole",

note = "{\textcopyright} 2006 Arne Risa Hole. The full text of this report can be viewed free of charge from the Centre for Health Economics web site at: http://www.york.ac.uk/inst/che/pdf/rp8.pdf",

year = "2006",

month = jan,

language = "English",

series = "CHE Research Paper",

publisher = "Centre for Health Economics, University of York",

}

TY - BOOK

T1 - A comparison of approaches to estimating confidence intervals for willingness to pay measures

AU - Hole, A.R.

PY - 2006/1

Y1 - 2006/1

N2 - This paper describes three approaches to estimating confidence intervals for willingness to pay measures, the delta, Krinsky and Robb and bootstrap methods. The accuracy of the various methods is compared using a number of simulated datasets. In the majority of the scenarios considered all three methods are found to be reasonably accurate as well as yielding similar results. The delta method is the most accurate when the data is well-conditioned, while the bootstrap is more robust to noisy data and misspecification of the model. These conclusions are illustrated by empirical data from a study of willingness to pay for a reduction in waiting time for a general practitioner appointment in which all the methods produce fairly similar confidence intervals.

AB - This paper describes three approaches to estimating confidence intervals for willingness to pay measures, the delta, Krinsky and Robb and bootstrap methods. The accuracy of the various methods is compared using a number of simulated datasets. In the majority of the scenarios considered all three methods are found to be reasonably accurate as well as yielding similar results. The delta method is the most accurate when the data is well-conditioned, while the bootstrap is more robust to noisy data and misspecification of the model. These conclusions are illustrated by empirical data from a study of willingness to pay for a reduction in waiting time for a general practitioner appointment in which all the methods produce fairly similar confidence intervals.

KW - willingness to pay

KW - confidence interval

KW - delta method

KW - boot-strap

M3 - Commissioned report

T3 - CHE Research Paper

BT - A comparison of approaches to estimating confidence intervals for willingness to pay measures

PB - Centre for Health Economics, University of York

CY - York, UK

ER -