Financial-market volatility prediction with multiplicative Markov-switching MIDAS componentsOpen Access

Schulte-Tillmann, Björn; Segnon, Mawuli; Wilfling, Bernd

Working paper

Abstract

We propose four multiplicative-component volatility MIDAS models to disentangle short- and long-term volatility sources. Three of our models specify short-term volatility as Markov-switching processes. We establish statistical properties, covariance-stationarity conditions, and an estimation framework using regime-switching filter techniques. A simulation study shows the robustness of the estimates against several mis-specifications. An out-of-sample forecasting analysis with daily S&P500 returns and quarterly-sampled (macro)economic variables yields two major results. (i) Specific long-term variables in the MIDAS models significantly improve forecast accuracy (over the non-MIDAS benchmarks). (ii) We robustly find superior performance of one Markov-switching MIDAS specification (among a set of competitor models) when using the 'Term structure' as the long-term variable.

Details about the publication

EditorsCenter for Quantitative Economics (CQE)
Place of publicationMünster
Title of seriesCQE Working Papers
Volume of series99/2022
StatusPublished
Release year2022 (13/06/2022)
Language in which the publication is writtenEnglish
Link to the full texthttps://www.wiwi.uni-muenster.de/cqe/de/publikationen/cqe-working-papers
KeywordsMIDAS volatility modeling; Hierarchical hidden Markov models; Markov-switching; Forecasting; Model confidence sets

Authors from the University of Münster

Schulte genannt Tillmann, Björn
Chair of Empirical Economics
Segnon, Mawuli Kouami
Professur für Volkswirtschaftslehre, empirische Wirtschaftsforschung (Prof. Wilfling)
Wilfling, Bernd
Professur für Volkswirtschaftslehre, empirische Wirtschaftsforschung (Prof. Wilfling)

Promotionen, aus denen die Publikation resultiert

Essays on Regime-Switching Models in Forecasting Financial-Market Data
Candidate: Schulte genannt Tillmann, Björn | Supervisors: Wilfling, Bernd; Trede, Mark | Reviewers: Wilfling, Bernd; Trede, Mark
Period of time: 01/04/2019 - 14/05/2024
Doctoral examination procedure finished at: Doctoral examination procedure at University of Münster