Effect of Income Heterogeneity on Valuation of Mortality Risk in Taiwan: An Application of Unconditional Quantile Regression Method

Abstract

According to theory and existing empirical results, heterogeneity in personal characteristics, with income variation being one of them, affects the marginal willingness to pay (WTP) for reducing fatal risk. In this study, the effect of income heterogeneity on the value of statistical life (VSL) in Taiwan through unconditional quantile regression analysis using the data collected by the “Manpower Utilization Survey” is investigated. The results of this empirical study show that the hedonic wage function that was constructed using empirical data from Taiwan was in line with the general form of non-linear function rather than the semi-log function that has been often used in previous studies, which should have great impact on the estimation of the VSL. The empirical results also show that the estimated VSL of Taiwanese labor varied with the difference in wages, which needs to be taken into account when discussing the public policies using VSL.

The Relationship between Cognitive Impairment and Social Vulnerability among the Elderly: Evidence from an Unconditional Quantile Regression Analysis in China

“…First, compared with OLS, the quantile regression estimator does not require a normal distribution of the sample data [18,28,29,30], thus is more practical for empirical studies, and is also able to measure the different relationships at all the cognitive impairment quantiles. Second, compared to a conditional quantile regression model (CQR), the unconditional quantile regression model has been found to have better properties [18] as the CQR is only able to measure the relationship between a quantile of the dependent variable (e.g., the 5th quantile of cognitive impairment) and the independent variable (social vulnerability), conditional on the specific values of the other covariates [28]; however, the coefficients obtained using the UQR can be interpreted as the relationships between the social vulnerability and the cognitive impairment with all other covariates as constant. This means that the UQR measures the relationship between social vulnerability and cognitive impairment at the quantiles regardless of all the other covariates [16,17]; therefore, UQR results are more policy-focused as it measures the unchangeable relationships of the main variables at different conditional quantiles [16].…”

“…Previous studies have generally obtained the coefficients using ordinary least squares (OLS) in the linear regression models [3,4,5,6,7,15]. However, OLS can only provide a partial view of the relationships as the relationships at different points in the conditional distribution of the dependent variables [16] cannot be described, and the robustness of the OLS results can decrease when there are outliers and a non-normal distribution [16,17,18].…”

Monetary Health Co-Benefits and GHG Emissions Reduction Benefits: Contribution from Private On-the-Road Transport

“…With the above data, the health co-benefits related to air pollution from PM 2.5 and its precursors, SO x and NO x , can be monetized. The benefit transfer method employed from a study by [ 60 ] in the estimation of VSL for Taiwan in 2014 accounts for the wage differentiation for different groups of people. Two other dimensions are considered to adjust for temporal differences between the years given the transfer of this value: the income difference and the price difference.…”

Monetary Health Co-benefits and GHG Emissions Reduction Benefits: Contribution from Private on-the-road Transport

“…With the above data, the health co-benefits related to air pollution from PM2.5 and its precursors SOx and NOx can be monetized. The benefit transfer method employed from a study by [60] in the estimation of VSL for Taiwan in 2014 accounts for wage differentiation for different groups of people. Two other dimensions are considered to adjust for temporal differences between the years given the transfer of this value: the income difference and the price difference.…”

“…Two other dimensions are considered to adjust for temporal differences between the years given the transfer of this value: the income difference and the price difference. According to [60], the income difference for the VSL can be adjusted as in ( 4…”