A new time-varying model for forecasting long-memory series
Methodology
2018-12-19 v1 Statistical Finance
Applications
Abstract
In this work we propose a new class of long-memory models with time-varying fractional parameter. In particular, the dynamics of the long-memory coefficient, , is specified through a stochastic recurrence equation driven by the score of the predictive likelihood, as suggested by Creal et al. (2013) and Harvey (2013). We demonstrate the validity of the proposed model by a Monte Carlo experiment and an application to two real time series.
Cite
@article{arxiv.1812.07295,
title = {A new time-varying model for forecasting long-memory series},
author = {Luisa Bisaglia and Matteo Grigoletto},
journal= {arXiv preprint arXiv:1812.07295},
year = {2018}
}