1

Introduction

My specialty, Bayesian statistics, conducts data analysis in a way that differs from the statistics you may be familiar with (classical statistics). In Bayesian statistics, unknown variables (such as the population mean) are treated as random variables that follow a distribution reflecting uncertainty about their values. The aim is to make inferences about these unknown variables by incorporating the information from observed data into this distribution. The theorem used to incorporate this data information is Bayes' theorem, which is why it's called Bayesian statistics. Bayesian statistics can also utilize information other than data (such as expert opinions or academic consensus), making it easy to use for decision-making under uncertainty, and it is increasingly being utilized in many fields.

Achievements

■Econometric Analysis of Japanese Rice Wine (Sake) Markets
・Research Objective: To conduct a comparative analysis of Japanese rice wine (sake) export trends between large firms in the Nada region and SMEs in other regions using econometric methods.
- Title: Comparative Analysis of Japanese Rice Wine Export Trends: Large Firms in the Nada Region vs. SMEs in Other Regions, Saito Wakuo, Nakakita Makoto, Nakatsuma Teruo （World） 5 （ 3 ） 700-722 Aug. 2024
・Research Objective: To formulate a hedonic pricing model for Japanese rice wine (sake) using hierarchical Bayesian modeling to examine the effects of producing regions, rice breeds, and taste characteristics on sake prices.
- Title: Hierarchical Bayesian hedonic regression analysis of Japanese rice wine: is the price right?, Saito Wakuo, Nakatsuma Teruo （International Journal of Wine Business Research） 35 （ 2 ） 256-277 May. 2023
■Econometric Analysis of Financial Markets
・Research Objective: To extend a stochastic conditional duration model to capture intraday seasonality and incorporate limit order book information.
- Title: Stochastic Conditional Duration Model with Intraday Seasonality and Limit Order Book Information, Toyabe Tomoki, Nakatsuma Teruo （Journal of Risk and Financial Management） 15 （ 10 ） 470 Oct. 2022
・Research Objective: To extend a stochastic volatility model for intraday high-frequency stock return data by incorporating intraday seasonality and skew heavy-tailed errors using Bayesian analysis.
- Title: Bayesian Analysis of Intraday Stochastic Volatility Models of High-Frequency Stock Returns with Skew Heavy-Tailed Errors, Nakakita Makoto, Nakatsuma Teruo （Journal of Risk and Financial Management） 14 （ 4 ） 145 Mar. 2021
・Research Objective: Improving volatility forecasts by proposing nonlinear generalizations of the leverage effect in stochastic volatility models.
- Title: Volatility forecasts using stochastic volatility models with nonlinear leverage effects, McAlinn Kenichiro, Ushio Asahi, Nakatsuma Teruo （Journal of Forecasting） 39 （ 2 ） 143-154 Mar. 2020
■Bayesian Estimation Methods for Stochastic Models
・Research Objective: To propose a modified block Gibbs sampler that ensures the positive definiteness of the precision matrix in Bayesian graphical models with shrinkage priors.
- Title: A positive-definiteness-assured block Gibbs sampler for Bayesian graphical models with shrinkage priors, Oya Sakae, Nakatsuma Teruo （Japanese Journal of Statistics and Data Science） 5 （ 1 ） 149-164 Jul. 2022
・Research Objective: To prpose a new Markov chain Monte Carlo method for Bayesian estimation of ARMA-GARCH models
- Title: Bayesian analysis of ARMA–GARCH models: A Markov chain sampling approach, Nakatsuma Teruo （Journal of Econometrics） 95 （ 1 ） 57-69 Mar. 2000

Areas of Research

・Statistical Science
・Econometrics

Social Contributions

・Enhancement of Market Dynamics Understanding
・Improvement of Trading Strategies
・Increase in Market Efficiency and Transparency
Video

The corresponding video could not be found.