Shinya Sugawara

Duopoly in the Japanese Airline Market : Bayesian Estimation for the Entry Game

This paper provides an econometric analysis of a duopoly game in the Japanese domestic airline market. We establish a novel Bayesian estimation approach for the entry game, which allows the incorporation of flexible inference techniques. We find asymmetric strategic interactions between Japanese firms. This result implies that competition is still influenced by the former regulation regime. Furthermore, our prediction analysis indicates that the new Shizuoka airport will suffer from a lack of demand in the future.

Firm‐Driven Management of Longevity Risk: Analysis of Lump‐Sum Forward Payments in Japanese Nursing Homes

This study analyzes a unique circumstance of longevity risk management in the Japanese private nursing home market. The circumstance takes the form of a lump-sum forward payment of lifetime rent by residents, which leaves most of the longevity risk to be covered by homes. To analyze this circumstance, I construct a structural econometric model of industrial organization for this market. For the underlying structure of the longevity risk, I assume that both individual consumers and nursing homes utilizes the subjective evaluation. My empirical analysis detects excess payments that can be compensated for only by an unrealistically long stay in nursing homes. This finding implies the existence of exaggerated evaluation of longevity by economic agents. Thus, appropriate government intervention to help hedging longevity risk might improve social welfare.

Gatekeeper Incentives and Demand Inducement: An Empirical Analysis of Care Managers in the Japanese Long-Term Care Insurance Program

This study analyzes the incentives and supplier-induced demand of care managers, who are intermediaries between consumers and service providers in the Japanese social insurance program for long-term care. Care managers can be considered as pure gatekeepers, in that their function is limited to referral people to specialists and they themselves do not provide care. Care managers are rewarded by capitation, which is considered as a cost-effective payment mechanism for insurers. However, many care managers actually work for firms that also operate as service providers. Service providers are rewarded by a fee-for-service payment and can have a motivation to induce excess consumer demand. The violation of the neutrality of care managers might result in a financial burden on social insurance. In this study, we empirically test whether there is a positive correlation between care manager density and care costs, which might imply the existence of supplier-induced demand. Our results show a positive correlation, particularly in the case of care managers who work for firms that jointly operate in service provision sectors. Based on these results, we conduct a quantitative analysis, and show that the demand induced by care managers might produce a considerable financial burden on social insurance.

A Basket Two-Part Model to Analyze Medical Expenditure on Interdependent Multiple Sectors

This study proposes a novel statistical methodology to analyze expenditure on multiple medical sectors using consumer data. Conventionally, medical expenditure has been analyzed by two-part models, which separately consider purchase decision and amount of expenditure. We extend the traditional two-part models by adding the step of basket analysis for dimension reduction. This new step enables us to analyze complicated interdependence between multiple sectors without an identification problem. As an empirical application for the proposed method, we analyze data of 13 medical sectors from the Medical Expenditure Panel Survey. In comparison with the results of previous studies that analyzed the multiple sector independently, our method provides more detailed implications of the impacts of individual socioeconomic status on the composition of joint purchases from multiple medical sectors; our method has a better prediction performance.

Decomposed Normalized Maximum Likelihood Codelength Criterion for Selecting Hierarchical Latent Variable Models

We propose a new model selection criterion based on the minimum description length principle in a name of the decomposed normalized maximum likelihood criterion. Our criterion can be applied to a large class of hierarchical latent variable models, such as the Naive Bayes models, stochastic block models and latent Dirichlet allocations, for which many conventional information criteria cannot be straightforwardly applied due to irregularity of latent variable models. Our method also has an advantage that it can be exactly evaluated without asymptotic approximation with small time complexity. Our experiments using synthetic and real data demonstrated validity of our method in terms of computational efficiency and model selection accuracy, while our criterion especially dominated the other criteria when sample size is small and when data are noisy.