A reality check on the GARCH-MIDAS volatility models

Nader Virk, Farrukh Javed, Basel Awartani, Stuart Hyde

Research output: Contribution to journalArticlepeer-review

41 Downloads (Pure)

Abstract

We employ a battery of model evaluation tests for a broad set of GARCH-MIDAS models and account for data snooping bias. We document that inferences based on standard tests for GM variance components can be misleading. Our data mining free results show that the gain of macro-variables in forecasting total (long-run) variance by GM models is overstated (understated). Estimation of different components of volatility is crucial for designing differentiated investing strategies, risk management plans and pricing derivative securities. Therefore, researchers and practitioners should be wary of data-mining bias, which may contaminate a forecast that may appear statistically validated using robust evaluation tests.

Original languageEnglish
JournalEuropean Journal of Finance
Early online date8 Jun 2023
DOIs
Publication statusE-pub ahead of print - 8 Jun 2023

Keywords

  • component variance forecasts
  • data snooping
  • Forecasting
  • GARCH-MIDAS models
  • macro-variables

Fingerprint

Dive into the research topics of 'A reality check on the GARCH-MIDAS volatility models'. Together they form a unique fingerprint.

Cite this