A Latent Factor Model for Forecasting Realized Volatilities

GSDS Working Paper No. 2017-14

55 Pages Posted: 17 Aug 2017

See all articles by Giorgio Calzolari

Giorgio Calzolari

Universita di Firenze - Dipartimento di Statistica

Roxana Halbleib

University of Konstanz

Aygul Zagidullina

University of Konstanz - Department of Economics

Date Written: July 2017

Abstract

This paper proposes a new method of forecasting realized volatilities by exploiting their common dynamics within a latent factor model. The main idea is to use an additive component structure to describe the long-persistence in their autocorrelation function, where the components, extracted from high-dimensional vectors of realized volatilities, follow stationary autoregressive processes of order 1. The model we propose allows also for autoregressive structures in the idiosyncratic noises and conditional hetersokedasticity. Differently from HAR and ARFIMA, our factor model profits from the high-dimensionality of the system that provides more information of the commonality of their dynamics with direct efficiency gains in the estimates and forecasts. For estimation purposes, we use the indirect inference method that is easy to implement and provides accurate estimates. We apply the new models to vectors of up to 30 daily realized volatility series of stocks composing the Dow Jones Industrial Average index and show that they outperform standard long-memory models both in-sample and out-of-sample.

Keywords: Long Memory, Component Model, Dynamic Factor Model, Factor-GARCH Model, Indirect Inference

Suggested Citation

Calzolari, Giorgio and Halbleib, Roxana and Zagidullina, Aygul, A Latent Factor Model for Forecasting Realized Volatilities (July 2017). GSDS Working Paper No. 2017-14, Available at SSRN: https://ssrn.com/abstract=3019144 or http://dx.doi.org/10.2139/ssrn.3019144

Giorgio Calzolari

Universita di Firenze - Dipartimento di Statistica ( email )

Viale Morgagni, 59
50134 Firenze
Italy
+39 055 4237 217 (Phone)
+39 055 4223 560 (Fax)

Roxana Halbleib (Contact Author)

University of Konstanz ( email )

Universitaetsstr. 10
Box: D 124
78457 Konstanz
Germany

HOME PAGE: http://econometrics.wiwi.uni-konstanz.de/staff/halbleib.htm

Aygul Zagidullina

University of Konstanz - Department of Economics ( email )

Konstanz, D-78457
Germany

Do you have negative results from your research you’d like to share?

Paper statistics

Downloads
206
Abstract Views
1,118
Rank
267,552
PlumX Metrics