Realized volatility forecasting: Robustness to measurement errors

B-Tier
Journal: International Journal of Forecasting
Year: 2021
Volume: 37
Issue: 1
Pages: 44-57

Score contribution per author:

0.670 = (α=2.01 / 3 authors) × 1.0x B-tier

α: calibrated so average coauthorship-adjusted count equals average raw count

Abstract

In this paper, we suggest how to handle the issue of the heteroskedasticity of measurement errors when specifying dynamic models for the conditional expectation of realized variance. We show that either adding a GARCH correction within an asymmetric extension of the HARclass (AHAR-GARCH), or working within the class of asymmetric multiplicative error models (AMEM) greatly reduces the need for quarticity/quadratic terms to capture attenuation bias. This feature in AMEM can be strengthened by considering regime specific dynamics. Model Confidence Sets confirm this robustness both in- and out-of-sample for a panel of 28 big caps and the S&P500 index.

Technical Details

RePEc Handle
repec:eee:intfor:v:37:y:2021:i:1:p:44-57
Journal Field
Econometrics
Author Count
3
Added to Database
2026-01-25