a new time varying model for forecasting long memory series

• DOI: 10.48550/arxiv.1812.07295
• Publication Date: 2020-03-02
• Authors: Bisaglia L.; Grigoletto M.
• Keywords: Methodology (stat.ME); FOS: Computer and information sciences; FOS: Economics and business; Statistical Finance (q-fin.ST); GAS model; Long-memory; Time-varying parameter; Quantitative Finance - Statistical Finance; Applications (stat.AP); Statistics - Applications; Statistics - Methodology

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, $d$, 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.