Марковська модель авторегресії із гетероскедастичними остачами

Time series forecasting by using the theory of Markov’s chains are considered. The main task was to find the transition probabilities for Markov’s chain on the basis of observed values of the time series. It is shown that to find the transition probabilities which meet all the necessary requirements...

Full description

Saved in:
Bibliographic Details
Date:2017
Main Authors: Matveev, A. A., Shadurskis, K. P.
Format: Article
Language:Russian
Published: The National Technical University of Ukraine "Igor Sikorsky Kyiv Polytechnic Institute" 2017
Online Access:http://journal.iasa.kpi.ua/article/view/109763
Tags: Add Tag
No Tags, Be the first to tag this record!
Journal Title:System research and information technologies

Institution

System research and information technologies
Description
Summary:Time series forecasting by using the theory of Markov’s chains are considered. The main task was to find the transition probabilities for Markov’s chain on the basis of observed values of the time series. It is shown that to find the transition probabilities which meet all the necessary requirements, one should use the quadratic programming on simplex. Consistent and unbiased estimations of the transition probabilities are built via the solution of the quadratic programming problem in MATLAB.