Abstract
Objectives
The application of Contingent Valuation (CV) is growing in health economics, particularly to quantify the monetary value of health gains. Protest responses, whereby respondents refuse to state the value they place on the health gain, are commonly encountered in CV studies, and they tend to be excluded from analysis. Inferences based solely on non-protesters may be biased because protesters tend to differ from non-protesters on observed and unobserved characteristics that predict their responses. The Heckman selection model has been commonly used to adjust for protesters, but its underlying assumptions may be implausible in this context. We present a Multiple Imputation (MI) approach to appropriately address protest responses in CV studies, and compare it to the Heckman selection model.
Methods
This study exploits data from the multinational EuroVaQ study, which surveyed respondents’ willingness-to-pay (WTP) for a Quality Adjusted Life Year (QALY). A simulation study assesses the relative performance of MI and Heckman selection models across different realistic settings grounded in the EuroVaQ study. We then illustrate the methods in the EuroVaQ study for estimating mean WTP for a QALY gain.
Results
We find that the MI provides lower bias and mean squared error compared to the Heckman approach across all scenarios considered, including different missing data mechanisms. The case study illustrates that, protesters are associated with a lower mean WTP for a QALY gain than non-protesters, but results differ according to method for handling protesters.
Conclusions
MI appears to be an appropriate method for addressing protest responses in CV studies.
The application of Contingent Valuation (CV) is growing in health economics, particularly to quantify the monetary value of health gains. Protest responses, whereby respondents refuse to state the value they place on the health gain, are commonly encountered in CV studies, and they tend to be excluded from analysis. Inferences based solely on non-protesters may be biased because protesters tend to differ from non-protesters on observed and unobserved characteristics that predict their responses. The Heckman selection model has been commonly used to adjust for protesters, but its underlying assumptions may be implausible in this context. We present a Multiple Imputation (MI) approach to appropriately address protest responses in CV studies, and compare it to the Heckman selection model.
Methods
This study exploits data from the multinational EuroVaQ study, which surveyed respondents’ willingness-to-pay (WTP) for a Quality Adjusted Life Year (QALY). A simulation study assesses the relative performance of MI and Heckman selection models across different realistic settings grounded in the EuroVaQ study. We then illustrate the methods in the EuroVaQ study for estimating mean WTP for a QALY gain.
Results
We find that the MI provides lower bias and mean squared error compared to the Heckman approach across all scenarios considered, including different missing data mechanisms. The case study illustrates that, protesters are associated with a lower mean WTP for a QALY gain than non-protesters, but results differ according to method for handling protesters.
Conclusions
MI appears to be an appropriate method for addressing protest responses in CV studies.
| Original language | English |
|---|---|
| Pages (from-to) | 623-634 |
| Number of pages | 12 |
| Journal | Medical Decision Making |
| Volume | 37 |
| Issue number | 6 |
| Early online date | 15 Feb 2017 |
| DOIs | |
| Publication status | Published - 1 Aug 2017 |
Keywords
- Heckman Selection
- Multiple Imputation
- Contingent Valuation
- missing data
- EuroVaQ