Measuring the effect of policy interventions at the population level: Some methodological concerns

Marco Huesch, Truls Østbye, Michael K. Ong

Research output: Contribution to journalArticle

12 Citations (Scopus)

Abstract

Health policy evaluations estimate the response of population aggregate outcomes to interventions. However, clarity on the form of the expected causal relationship, the parameter identification strategy, and the mode of hypothesis testing is required to overcome a number of conceptual and methodological problems. We use the New Jersey statewide smoking ban as an example. We examine statewide admission rates for acute myocardial infarctions, strokes and lower limb fractures, and emergency room encounter rates for asthma exacerbations before and after the smoking ban. We discuss the identification options and show the sensitivity of estimates of the response function to different specifications of the stochastic and intervention components and to different modes of inference. Model misspecification is demonstrated by rolling Chow tests for structural breaks in repeated observations.

Original languageEnglish (US)
Pages (from-to)1234-1249
Number of pages16
JournalHealth Economics (United Kingdom)
Volume21
Issue number10
DOIs
StatePublished - Oct 1 2012

Fingerprint

Smoking
Health Policy
Population
Hospital Emergency Service
Lower Extremity
Asthma
Stroke
Myocardial Infarction

All Science Journal Classification (ASJC) codes

  • Health Policy

Cite this

Huesch, Marco ; Østbye, Truls ; Ong, Michael K. / Measuring the effect of policy interventions at the population level : Some methodological concerns. In: Health Economics (United Kingdom). 2012 ; Vol. 21, No. 10. pp. 1234-1249.
@article{9c174e26e5f7441691e47b89d6e57b13,
title = "Measuring the effect of policy interventions at the population level: Some methodological concerns",
abstract = "Health policy evaluations estimate the response of population aggregate outcomes to interventions. However, clarity on the form of the expected causal relationship, the parameter identification strategy, and the mode of hypothesis testing is required to overcome a number of conceptual and methodological problems. We use the New Jersey statewide smoking ban as an example. We examine statewide admission rates for acute myocardial infarctions, strokes and lower limb fractures, and emergency room encounter rates for asthma exacerbations before and after the smoking ban. We discuss the identification options and show the sensitivity of estimates of the response function to different specifications of the stochastic and intervention components and to different modes of inference. Model misspecification is demonstrated by rolling Chow tests for structural breaks in repeated observations.",
author = "Marco Huesch and Truls {\O}stbye and Ong, {Michael K.}",
year = "2012",
month = "10",
day = "1",
doi = "10.1002/hec.1783",
language = "English (US)",
volume = "21",
pages = "1234--1249",
journal = "Health Economics",
issn = "1057-9230",
publisher = "John Wiley and Sons Ltd",
number = "10",

}

Measuring the effect of policy interventions at the population level : Some methodological concerns. / Huesch, Marco; Østbye, Truls; Ong, Michael K.

In: Health Economics (United Kingdom), Vol. 21, No. 10, 01.10.2012, p. 1234-1249.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Measuring the effect of policy interventions at the population level

T2 - Some methodological concerns

AU - Huesch, Marco

AU - Østbye, Truls

AU - Ong, Michael K.

PY - 2012/10/1

Y1 - 2012/10/1

N2 - Health policy evaluations estimate the response of population aggregate outcomes to interventions. However, clarity on the form of the expected causal relationship, the parameter identification strategy, and the mode of hypothesis testing is required to overcome a number of conceptual and methodological problems. We use the New Jersey statewide smoking ban as an example. We examine statewide admission rates for acute myocardial infarctions, strokes and lower limb fractures, and emergency room encounter rates for asthma exacerbations before and after the smoking ban. We discuss the identification options and show the sensitivity of estimates of the response function to different specifications of the stochastic and intervention components and to different modes of inference. Model misspecification is demonstrated by rolling Chow tests for structural breaks in repeated observations.

AB - Health policy evaluations estimate the response of population aggregate outcomes to interventions. However, clarity on the form of the expected causal relationship, the parameter identification strategy, and the mode of hypothesis testing is required to overcome a number of conceptual and methodological problems. We use the New Jersey statewide smoking ban as an example. We examine statewide admission rates for acute myocardial infarctions, strokes and lower limb fractures, and emergency room encounter rates for asthma exacerbations before and after the smoking ban. We discuss the identification options and show the sensitivity of estimates of the response function to different specifications of the stochastic and intervention components and to different modes of inference. Model misspecification is demonstrated by rolling Chow tests for structural breaks in repeated observations.

UR - http://www.scopus.com/inward/record.url?scp=84865860877&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84865860877&partnerID=8YFLogxK

U2 - 10.1002/hec.1783

DO - 10.1002/hec.1783

M3 - Article

C2 - 21887723

AN - SCOPUS:84865860877

VL - 21

SP - 1234

EP - 1249

JO - Health Economics

JF - Health Economics

SN - 1057-9230

IS - 10

ER -