This paper adopted the quantile regression (QR) estimator to assess the effects of the medical utilization factors (changes to the health care system, the insured individual’s demographic and health risk factors) across the whole conditional distribution, and to provide a more complete picture of this relationship. The findings indicated that some of these factors have a significant impact on their medical utilization. Furthermore, we analyzed the probable causes leading to the variations in the medical risk costs of a person. The empirical results of this study confirm the evidence of right skewness, as well as the existence of outliers at the highest tail of the medical utilization distribution in Taiwan.
The empirical results of this study can serve as a reference when determining new premium rates and deductibles to resolve the serious financial crisis Taiwan’s National Health Insurance (NHI) finds itself in today.
Keywords: quantile regression, medical risk costs, medical utilization, co-payment, global budget