A0293
Title: Does long-term care reduce health care utilization? A novel nonparametric dynamic panel mediation estimation approach
Authors: Andrej Srakar - Institute for Economic Research Ljubljana (Slovenia) [presenting]
Abstract: The causal relationship between long-term care and healthcare utilization of the elderly is addressed. The expansion of long-term care (LTC) may improve health system efficiency by reducing hospitalisations, and pave the way for implementation of health and social care coordination plans. The longitudinal evidence from the survey of health, ageing and retirement in Europe (SHARE) is drawn upon to derive causal estimates of the effects of receiving different types of LTC on healthcare utilization. The causal problem with health indicators as mediators is analyzed. Multiple reverse causality is solved by using cross-lagged panel models, a form of longitudinal mediation analysis. As the latter is based on strong Gaussianity assumptions, two novel estimators are constructed: a nonparametric, based on iterative kernel estimation of dynamic panel mediation using sieves based on Laguerre polynomials as consistent initial estimators and a Bayesian nonparametric, based on autoregressive Dirichlet process mixtures for longitudinal data used in combination with a dynamic Bayesian modelling approach. Results are provided on the performance of the estimators, namely asymptotics and simulation experiments. Empirical results are provided confirming the significant effects of LTC provision on reducing healthcare utilization and estimates of the reduction of costs in several Central and Eastern European countries' healthcare systems due to proposed measures in long-term care.
