Markov Switching Panel with Network Interaction Effects

发布时间:2019-05-22

讲座时间:2019年522日 上午10:00 - 11:30

讲座地点:创管学院320会议室

讲座嘉宾Ravazzolo Francesco (Free University of Bozen/Bolzano教授

邀请人:杨乔


讲座内容简介: 

The paper introduces a new dynamic panel model for large data sets of time series, each of them characterized by a series-specific Markov switching process. By introducing a neighbourhood system based on a network structure, the model accounts for local and global interactions among the switching processes. We develop an efficient Markov Chain Monte Carlo (MCMC) algorithm for the posterior approximation based on the Metropolis adjusted Langevin sampling method. We study efficiency and convergence of the proposed MCMC algorithm through several simulation experiments. In the empirical application, we deal with US states coincident indices, produced by the Federal Reserve Bank of Philadelphia, and find evidence that local interactions of state-level cycles with geographically and economically networks play a substantial role in the common movements of US regional business cycles.


讲座嘉宾简介: 

Francesco Ravazzolo is Full Professor of Econometrics at Faculty of Economics and Management at Free University of Bozen/Bolzano and visiting Professor at Center for Applied Macro and commodity Prices, BI Norwegian Business School
His research focuses on Bayesian econometrics, energy economics, financial econometrics and macroeconometrics. He has published in several leading academic journals. 
Francesco serves the academia in several roles: he is in the editorial board of the following journals: 
Annals of Applied StatisticsInternational Journal of ForecastingJournal of Applied EconometricsStudies in Nonlinear Dynamics and Econometrics. He is also member of the executive committee of Society of Nonlinear Dynamics and Econometrics. His activities have been reviewed in several newspapers and magazines, such as Wall Street JournalThe TelegraphCorriere della SeraAcademia.