Year: 2000
Type: report
Abstract: We propose a new GARCH model with tree-structured multiple thresholds for volatility estimation in nancial time series. The approach relies on the idea of a binary tree where every terminal node parameterizes a (local) GARCH model for a partition cell of the predictor space. Fitting of such trees is constructed within the likelihood framework for non-Gaussian observations: it is very dierent from the well-known CART procedure for regression based on residual sum of squares. Our strategy includes the classical GARCH model and allows in a systematic and exible way to increase model-complexity. We conclude with simulations and real data analysis that the new method has better predictive potential compared to other approaches. Keywords: Conditional variance; Financial time series; GARCH model; Maximum likelihood; Threshold model; Tree model. 1 Introduction We propose a new method for estimating volatility in stationary nancial time series; our real data examples are daily log-returns...
Authors: Audrino, Francesco, Bühlmann, Peter
Language: English
Subfield: Finance
Domain: Social Sciences
Open Access status: green
OpenAlex ID: W1598203952