z-logo
Premium
USING COST‐EFFECTIVENESS ESTIMATES FROM SURVEY DATA TO GUIDE COMMISSIONING: AN APPLICATION TO HOME CARE
Author(s) -
Forder Julien,
Malley Juliette,
Towers AnnMarie,
Netten Ann
Publication year - 2014
Publication title -
health economics
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 1.55
H-Index - 109
eISSN - 1099-1050
pISSN - 1057-9230
DOI - 10.1002/hec.2973
Subject(s) - endogeneity , counterfactual thinking , estimation , instrumental variable , survey data collection , computer science , econometrics , actuarial science , quality (philosophy) , function (biology) , service (business) , project commissioning , missing data , risk analysis (engineering) , statistics , medicine , economics , business , marketing , mathematics , psychology , publishing , biology , social psychology , philosophy , management , epistemology , evolutionary biology , political science , law
The aim is to describe and trial a pragmatic method to produce estimates of the incremental cost‐effectiveness of care services from survey data. The main challenge is in estimating the counterfactual; that is, what the patient's quality of life would be if they did not receive that level of service. A production function method is presented, which seeks to distinguish the variation in care‐related quality of life in the data that is due to service use as opposed to other factors. A problem is that relevant need factors also affect the amount of service used and therefore any missing factors could create endogeneity bias. Instrumental variable estimation can mitigate this problem. This method was applied to a survey of older people using home care as a proof of concept. In the analysis, we were able to estimate a quality‐of‐life production function using survey data with the expected form and robust estimation diagnostics. The practical advantages with this method are clear, but there are limitations. It is computationally complex, and there is a risk of misspecification and biased results, particularly with IV estimation. One strategy would be to use this method to produce preliminary estimates, with a full trial conducted thereafter, if indicated. Copyright © 2013 John Wiley & Sons, Ltd.

This content is not available in your region!

Continue researching here.

Having issues? You can contact us here