| Title |
EM Algorithm for Estimating the Parameters of the Multivariate Stable Distribution / |
| Authors |
Sakalauskas, Leonidas ; Vaičiulytė, Ingrida |
| Full Text |
|
| Is Part of |
SMTDA 2018 : Procceedings of the 5th Stochastic Modeling Techniques and Data Analysis International Conference with Demographics Workshop Chania, Crete, Greece: 12-15 June, 2018.. Chania : International Society for the Advancement of Science and Technology. 2018, p. 509-519 |
| Keywords [eng] |
Gaussian and alpha-stable model ; EM algorithm ; Likelihood ratio test ; Quadrature formulas |
| Abstract [eng] |
Research of alpha-stable distributions is especially important nowadays, because they often occur in the analysis of financial data and information flows along computer networks. It has been found that financial data are often leptokurtic with a heavy-tailed distributions; many authors, e.g., Rachev, Mittnik (2000), Kabasinskas et al. (2012), Sakalauskas et al. (2013) have proved that the most often used normal distribution is not the most suitable way to analysis economic indicators and suggested to replace it with more general, for example, stable distributions. Since Rachev, Mittnik (2000), Kabasinskas et al. (2012), Sakalauskas et al. (2013) have estimated one-dimensional alpha-stable distributions a problem arises how to estimate multidimensional data. Maximum likelihood method for the estimation of multivariate alpha-stable distributions by using EM algorithm is presented in this work. Integrals included in the expressions of the estimates have been calculated using the Gaussian and Gauss-Laguerre quadrature formulas. The constructed model can be used in stock market data analysis. |
| Published |
Chania : International Society for the Advancement of Science and Technology |
| Type |
Conference paper |
| Language |
English |
| Publication date |
2018 |
