RT Generic
T1 A semiparametric Bayesian approach to the analysis of financial time series with applications to value at risk estimation
A1 Ausín Olivera, María Concepción
A1 Galeano, Pedro
A1 Ghosh, Pulak
A2 Universidad Carlos III de Madrid. Departamento de Estadística, 
AB Financial time series analysis deals with the understanding of data collected on financialmarkets. Several parametric distribution models have been entertained for describing,estimating and predicting the dynamics of financial time series. Alternatively, thisarticle considers a Bayesian semiparametric approach. In particular, the usualparametric distributional assumptions of the GARCH-type models are relaxed byentertaining the class of location-scale mixtures of Gaussian distributions with aDirichlet process prior on the mixing distribution, leading to a Dirichlet process mixturemodel. The proposed specification allows for a greater exibility in capturing both theskewness and kurtosis frequently observed in financial returns. The Bayesian modelprovides statistical inference with finite sample validity. Furthermore, it is also possibleto obtain predictive distributions for the Value at Risk (VaR), which has become themost widely used measure of market risk for practitioners. Through a simulation study,we demonstrate the performance of the proposed semiparametric method and compareresults with the ones from a normal distribution assumption. We also demonstrate thesuperiority of our proposed semiparametric method using real data from the BombayStock Exchange Index (BSE-30) and the Hang Seng Index (HSI).
YR 2010
FD 2010-09
LK https://hdl.handle.net/10016/9283
UL https://hdl.handle.net/10016/9283
LA eng
DS e-Archivo
RD 30 jun. 2024