Relative performance of VIXC vs. GARCH in predicting realised volatility changes

Abstract

This paper examines the forecasting power of the volatility index of Canada (VIXC) and GARCH-family volatility. Specifically, this paper is motivated by an enquiry into how well volatility estimators predict volatility changes. To this end, we use a daily series of VIXC from 1 October 2009 through 30 April 2015. To estimate out-of-sample parameters for GARCH volatilities, a series of daily returns of the TSX60 since 29 November 2002 is used roll-forwardly. Then we run the forecasting regressions for a full-sample and five subsamples grouped by the daily percentage change in realised volatility, and compare R 2 and the loss functions to assess the forecasting power of volatility estimators. Additionally, this paper proposes a new measurement called mean-directional-error (MDE), which can comprehensively evaluate the forecast error in both direction and size of movement. The key findings of this paper can be summarised as follows: even though the information content of VIXC is highest on average and intensifies when volatility falls high, the directional accuracy measured by MDE is worst for VIXC in all subsamples. GJR-GARCH (1,1) achieves the highest accuracy judged by the traditional loss functions. Focusing on the directional accuracy, GARCH (1,1) demonstrates the best predictability. ARTICLE HISTORY

Predictability of OTC Option Volatility for Future Stock Volatility

“…For example, Luo et al [32] provide evidence that the CBOE gold ETF volatility index has substantial forecasting power for realized volatility of the Shanghai gold futures market in in-sample and out-of-sample tests. Jung [33] explored the predictability of the Volatility Index of Canada (VIXC) compared with those of GARCH type volatility and found that the VIXC exhibits the worst predictability and GARCH (1,1) makes the best predictions when considering the directional accuracy measured by mean directional error.…”

Analysis of Relationship Between BIST-100 and BIST Sector Indices with VIX Index

“…Uluslararası piyasalarda volatilite göstergesi olarak kabul edilen VIX endeksi, bir çok çalışmada yer almıştır. Çeşitli çalışmalarda piyasaların gelecek volatiliteleri ile ilgili olarak endeksin tahmin gücü araştırılmış (Poon ve Granger, 2003;Corrado ve Miller, 2005;Banerjee and Kumar, 2011;Jung, 2016;Emna ve Myriam, 2017), diğer taraftan bazı çalışmalarda da VIX endeksinin hisse senedi getirileri ile ilişkileri incelenmiştir. Bu çalışmada VIX endeksi ile BİST Ulusal 100, BİST Banka, BİST Mali ve BİST Teknoloji endeksleri arasındaki ilişkiler araştırılacağı için, literatür incelemesinde de bu kapsamdaki ilişkiler açıklanmaktadır.…”

Risk of investing in volatility products: A regime-switching approach

“…The literature on risk measurement outlines a set of models to estimate the conditional second moments of asset value. For the conditional variance, Engle's (1982) autoregressive conditional heteroskedasticity (ARCH) model and Bollweslev's (1986) generalised ARCH (GARCH) model are the most commonly-used methods (see Thupayagale, 2010;Jung, 2016) while the dynamic conditional correlation (DCC) model, proposed by Engle (2002), is the most popular (see Park et al, 2019) for the conditional correlation. It should be noted that Engle's (2002) DCC model uses a pure and simple time-varying process: it employs the correlations in the past to estimate the future correlations, and thus is unable to identify the common factors which drive the dynamics of conditional correlations.…”