Statistical Methods in Finance 2016

Dec 18 - 22, 2016


Abstract

Cointegration models with non Gaussian GARCH innovations

by Nimitha John

A bivariate Cointegration time series model with time varying conditional variances and covariances is proposed. We discuss the estimation procedures by using Fisher Scoring algorithm and numerical likelihood optimization technique when the errors follow some GARCH models. A simulation study is carried out to illustrate the finite sample properties of the proposed estimators. Since the model leads to resosonable financial interpretations, the proposed model is used to analyse several price series.