Title :
On the top-Lyapunov exponent of block-triangular stationary random matrices
Author :
Gerencser, Laszlo ; Michaletzky, Gyorgy ; Orlovits, Zsanett
Author_Institution :
MTA SZTAKI, Comput. & Autom. Inst., Budapest, Hungary
Abstract :
The objective of this note is to prove a useful, nontrivial technical lemma that is needed in the statistical analysis of linear stochastic systems with random system matrices. This study is motivated by the study of the quasi-maximum-likelihood identification method of certain stochastic volatility processes, called the GARCH (Generalized Autoregressive Conditional Heteroscedasticity) processes.
Keywords :
Lyapunov methods; autoregressive processes; linear systems; matrix algebra; maximum likelihood estimation; random processes; statistical analysis; stochastic processes; stochastic systems; GARCH processes; block-triangular stationary random matrices; generalized autoregressive conditional heteroscedasticity; linear stochastic systems; quasimaximum-likelihood identification method; statistical analysis; stochastic volatility processes; top-Lyapunov exponent; Equations; Mathematical model; Random variables; Stochastic systems; Upper bound; Vectors; Writing; GARCH processes; Lyapunov-exponent; almost sure exponential stability; identification; random coefficient linear stochastic systems; random matrix products; stochastic volatility;
Conference_Titel :
Control Conference (ECC), 2007 European
Conference_Location :
Kos
Print_ISBN :
978-3-9524173-8-6
