Abstract. This paper describes a GAUSS program of a Markov-chain sampling algorithm for GARCH models proposed by Nakatsuma (1998
The leverage effect-the correlation between an asset's return and its volatility-has played a key role in forecasting and understanding volatility and risk. While it is a long standing consensus that leverage effects exist and improve forecasts, empirical evidence paradoxically do not show that most individual stocks exhibit this phenomena, mischaracterizing risk and therefore leading to poor predictive performance. We examine this paradox, with the goal to improve density forecasts, by relaxing the assumption of linearity in the leverage effect. Nonlinear generalizations of the leverage effect are proposed within the Bayesian stochastic volatility framework in order to capture flexible leverage structures, where small fluctuations in prices have a different effect from large shocks. Efficient Bayesian sequential computation is developed and implemented to estimate this effect in a practical, on-line manner. Examining 615 stocks that comprise the S&P500 and Nikkei 225, we find that relaxing the linear assumption to our proposed nonlinear leverage effect function improves predictive performances for 89% of all stocks compared to the conventional model assumption.
A Bayesian Study On Social Media Language During The First Wave of the COVID-19 Pandemic.Personality traits change over time, however research on it was sparse, since previous approaches were too time-consuming and expensive. Also, the necessary methodological complexity was beyond the capabilities of classical personality researchers, which resulted in contradictory results and lack of methodological standards. In this paper, we presented a simple and cost-effective method that overcame these restrictions.We introduced a machine learning approach for daily measurements to personality research, and developed a bespoke Bayesian algorithm to analyse the observed change. This resulted in uncovering concrete points of regime-shift that overlapped with relevant exogenous events for a Japanese sample of social media users.With it, we showed that personality measures displayed significant elasticity under extreme exogenous conditions during the first wave of COVID-19 and the subsequent societal countermeasures, which can be interpreted as a temporary shift from normal expression of latent psychological traits z to their respective emergency expression ze.Concretely, we found that the group of top 25% Conscientiousness users displayed a significant change in the FFM factors Agreeableness and Extraversion. We finally compared our findings with those from similar studies in other cultures, and discussed generalisability as well as future qualitative and quantitative directions for research.
Purpose This paper aims to formulate a hedonic pricing model for Japanese rice wine, sake, via hierarchical Bayesian modeling estimated using an efficient Markov chain Monte Carlo (MCMC) method. Using the estimated model, the authors examine how producing regions, rice breeds and taste characteristics affect sake prices. Design/methodology/approach The datasets in the estimation consist of cross-sectional observations of 403 sake brands, which include sake prices, taste indicators, premium categories, rice breeds and regional dummy variables. Data were retrieved from Rakuten, Japan’s largest online shopping site. The authors used the Bayesian estimation of the hedonic pricing model and used an ancillarity–sufficiency interweaving strategy to improve the sampling efficiency of MCMC. Findings The estimation results indicate that Japanese consumers value sweeter sake more, and the price of sake reflects the cost of rice preprocessing only for the most-expensive category of sake. No distinctive differences were identified among rice breeds or producing regions in the hedonic pricing model. Originality/value To the best of the authors’ knowledge, this study is the first to estimate a hedonic pricing model of sake, despite the rich literature on alcoholic beverages. The findings may contribute new insights into consumer preference and proper pricing for sake breweries and distributors venturing into the e-commerce market.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
customersupport@researchsolutions.com
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.