We propose an econometric procedure based mainly on the generalized random forests method. Not only does this process estimate the quantile treatment effect nonparametrically, but our procedure yields a measure of variable importance in terms of heterogeneity among control variables. We also apply the proposed procedure to reinvestigate the distributional effect of 401(k) participation on net financial assets, and the quantile earnings effect of participating in a job training program.

No abstract

Background Whether long-term care service use decreases older adults’ health care service use and cost has been a strong interest among aging countries, including Taiwan. The current study examined the impact of continuous use of HCBS offered by Taiwan’s LTC plan 2.0 on older adults’ health service utilization and cost overtime. Methods This study used the LTC Plan 2.0 database and the National Health Insurance Plan claim dataset, and included 151,548 clients who had applied for and were evaluated for LTC services for the first time from 2017 through 2019 and continuously used any LTC Plan 2.0 services for six months. Outcome variables were users’ health service utilization and health care cost 12 months before and after starting to continuously use HCBS. Latent class analysis and generalized estimating equations were used to investigate the influences of different service use patterns on the changes in physical functions. Results Three subgroups of LTC recipients with different use patterns, including home-based personal care (home-based PC) services (n = 107324, 70.8%), professional care services (n = 30466, 20.1%), and community care services (n = 13794, 9.1%) were identified. When compared to care recipients in the community care group, those in the home-based PC group had more emergency room expenditures (1 point/month, p< 0.05) but less hospitalization expenditures (38 points/month, p<0.001), while the professional care group had less emergency room and hospitalization expenditures (3 and 138 points/month, p< 0.001). Conclusion Those receiving professional care and home care services spent less on health care service utilization.

No abstract

One of the core issues in long-term care (LTC) policy is the growing imbalance between demand and supply of LTC services due to aging population. To estimate the imbalance and allocate LTC resources, the government regularly conducts surveys. These surveys are expensive given the sample size requirements and imprecise given their subjective nature. This study links the administrative records of the universal health insurance database with LTC program usage records in Taiwan to explore this issue. Machine learning algorithms are used in projecting LTC needs from administrative records. LTC program usage records provide detailed LTC needs information and the amount of service each individual used. In addition, health insurance claim data provides rich health information. Specific LTC needs are predicted for each individual. By further extrapolating to future demographics, long-term LTC needs could be projected. There are several findings in this study. Prediction of difficulties in activities of daily livings (ADL), measured by Barthel index, works best using the Gradient Boosting algorithm. The mean absolute error is 17.67 out of a 0 to 100 scale. In addition to dementia and stroke, diagnosis of pressure ulcer (ICD 10 code: L89) and pneumonia (ICD 10 code: J18) have high predictive power for LTC needs. Prediction of Instrumental ADL (IADL) also performs well with a mean absolute error 1.31. The prediction model suggests high LTC needs and excess demand as the demographics changing. Our study provides a reliable way of using rich information to estimate future LTC needs without conducting additional costly surveys.