A Estimation of Stochastic Volatility Models Using Optimized Filtering Algorithms

Austrian Journal of Statistics

article

Saba Infante¹  Cesar Luna²  Luis Sanchez³  Aracelis Hernández² 

[1] Yachay Tech;Universidad de Carabobo;Universidad Técnica de Manabí

关键词: stochastic volatility models;    optimized particle filter;    Viterbi algorithm;   

DOI  :  10.17713/ajs.v48i2.803

学科分类：医学（综合）

来源: Austrian Statistical Society

【 摘 要 】

In this paper, we describe and implement two recursive filtering algorithms, the optimized particle filter, and the Viterbi algorithm, which allow the joint estimation of statesand parameters of continuous-time stochastic volatility models, such as the Cox IngersollRoss and Heston model. In practice, good parameter estimates are required so that themodels are able to generate accurate forecasts. To achieve the objectives the proposed algorithms were implemented using daily empirical data from the time series of the S&P500returns of the stock exchange index. The proposed methodology facilitates computationalcalculations of the marginal likelihood of states and allows the reconstruction of unknownstates in a suitable way, and reliable estimation of the parameters. To measure the quality of estimation of the algorithms, we used the square root of the mean square errorand relative deviation standard as measures of goodness of fit. The estimated errors areinsignificant for the analyzed data and the two models considered. We also calculatedthe execution times of the algorithms, demonstrating that the Viterbi algorithm has lessexecution time than the optimized particle filter.

【 授权许可】

CC BY