Presentation 2005-06-23
Estimation of GARCH-Type Time Series Models using Monte Carlo Filter and the Genetic Programming and its Applications
Yoshikazu IKEDA, Shozo TOKINAGA,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) Among various nonlinear model fitting methods, ARCH and GARCH are developed to describe the model for the volatility. However, conventional GARCH type models usually postulate fixed functtional form included in models, and it is not clear the fitted model is the best one. In this report, we propose the estimation of GARCH-Type models with Markov switching using Monte Carlo filter and the Genetic Programming (GP). The functional forms of dynamics are estimated by using the GP, and the states are estimated based on the Monte Carlo filters. The method is applied to the estiamtion of GARCH models for known systems, and then applied to real world data.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) Genetic Programming / GARCH / monte carlo filter
Paper # NLP2005-18
Date of Issue

Conference Information
Committee NLP
Conference Date 2005/6/16(1days)
Place (in Japanese) (See Japanese page)
Place (in English)
Topics (in Japanese) (See Japanese page)
Topics (in English)
Chair
Vice Chair
Secretary
Assistant

Paper Information
Registration To Nonlinear Problems (NLP)
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) Estimation of GARCH-Type Time Series Models using Monte Carlo Filter and the Genetic Programming and its Applications
Sub Title (in English)
Keyword(1) Genetic Programming
Keyword(2) GARCH
Keyword(3) monte carlo filter
1st Author's Name Yoshikazu IKEDA
1st Author's Affiliation Faculty of Economics, Shinshu University()
2nd Author's Name Shozo TOKINAGA
2nd Author's Affiliation Graduate School of Economics, Kyushu University
Date 2005-06-23
Paper # NLP2005-18
Volume (vol) vol.105
Number (no) 125
Page pp.pp.-
#Pages 6
Date of Issue