- This event has passed.
Hidden Markov structures for dynamic copulae
23 October, 2017 @ 13:00 - 14:00 UTC+1
“Hidden Markov structures for dynamic copulae” is the title of the lecture that Weining Wang (Humboldt-Universität zu Berlin (Germany= and King’s College (London)) is going to present in the Department of Economics of the University of Cantabria. The talk will take place next October 23st at 13.00 in the Degree Room of the Faculty of Economic and Business and is concerning about the following.
Abstract: Understanding the time series dynamics of a multi-dimensional dependency structure is a challenging task. Multivariate covariance driven Gaussian or mixed normal time varying models have only a limited ability to capture important features of the data such as heavy tails, asymmetry, and nonlinear dependencies. The present paper tackles this problem by proposing and analyzing a hidden Markov model (HMM) for hierarchical Archimedean copulae (HAC). The HAC constitute a wide class of models for multi-dimensional dependencies, and HMM is a statistical technique for describing regime switching dynamics. HMM applied to HAC flexibly models multivariate dimensional non-Gaussian time series. We apply the expectation maximization (EM) algorithm for parameter estimation. Consistency results for both parameters and HAC structures are established in an HMM framework. The model is calibrated to exchange rate data with a VaR application. This example is motivated by a local adaptive analysis that yields a time varying HAC model. We compare its forecasting performance with that of other classical dynamic models. In another, second, application, we model a rainfall process. This task is of particular theoretical and practical interest because of the specific structure and required untypical treatment of precipitation data.
This research seminar is part of the activities of the research project “New methods for the empirical analysis of the financial markets” financed by the Santander Financial Institute (SANFI) within the strategic line of the SANFI called Global Markets. This research project is led by Professor Oliver Linton (University of Cambridge) and has as coordinators Professors Juan Rodriguez-Poo (University of Cantabria) and Francisco Peñaranda (City University of New York). Specifically, the objective of this research project is mainly focused on the development of new techniques of estimation of application both in the valuation of financial assets and in the management of risks and portfolios.
Weining Wang is a Junior Professor of Nonparametric Statistics and Dynamic Risk Management at the Humboldt-Universität zu Berlin. She holds degrees from the Humboldt-Universität zu Berlin (master in Statistics and PhD in Economics).
Dr. Wang published mainly on statistics methodology with applications in finance, economics, and social science. In particular, she works on nonparametric and semiparametric statistics for time series analysis. Her doctoral thesis concentrates on using adaptive methods to calibrate risk in financial markets. In addition, she has published extensively in top-ranked international journals such as Journal of Business and Economic Statistics, Journal of Financial Econometrics, Journal of Statistical Planning and Inference, and Journal of Econometrics. Also, she has written several book chapters about risk calibration.