A Dynamic Optimization Model Incorporating the VIX Index to Predict Future Returns Open Access

Abstract

Abstract
A Dynamic Optimization Model Incorporating the VIX Index to Predict Future Returns
By Andrew G. Joy
This paper demonstrates that there is a significant relationship between a periods change in the VIX index
and future asset returns for the data tested on six mutual funds. Each of the six funds has a negative
relationship with the VIX index, indicating an increase in expected market volatility is associated with
decreased future asset returns. However, as expected, there is a significant amount of variance in the
intercept terms and the beta coefficients between the assets, indicating that some assets are more sensitive
to a given change in the VIX index. Additionally, through several out-of-sample simulations, a portfolio
that incorporates the VIX index to project future asset returns, while holding constant variances, co-
variances, and expected returns outperformed both the standard mean-variance optimization using static
estimates, as well as the equally weighted (1/N) portfolio. The VIX optimized portfolio outperformed the
other two portfolios in several aspects, including total return as well as return/risk performance ratios. The
benefits of the VIX index is especially useful during bear markets, as losses were substantially minimized
during market downturns compared with the other two portfolios. In addition, the data in this paper
supports the theory that large increases in expected volatility may be an indicator of an oversold market.
This is demonstrated by the fact that the optimal VIX portfolio increased its positions in riskier assets and
reduced its position in safer assets subsequent to a rise in expected implied market volatility represented by
a change in the VIX index.

Table of Contents

TABLE OF CONTENTS

I. INTRODUCTION

II. UNDERSTANDING THE VIX
III. DATA DESCRIPTION
IV. METHODOLOGY
a. STANDARD OPTIMIZATION AND EQUALLY WEIGHTED PORTFOLIO
b. VIX OPTIMIZATION MODEL

V. RESULTS
a. VIX INDEX AND FUND REGRESSIONS
b. OUT-OF-SAMPLE SIMULATIONS
c. TOTAL PERIOD PERFORMANCE
d. PERFORMANCE DURING THE FINANCIAL CRISIS
e. VIX MODEL ASSET WEIGHTS
d. STANDARD MARKOWITZ ASSET WEIGHTS
VI. BRIEF CONCLUSION AND ADDITIONAL RESEARCH
VII. EXHIBITS
VIII. REFERENCES

About this Honors Thesis

Rights statement

• Permission granted by the author to include this thesis or dissertation in this repository. All rights reserved by the author. Please contact the author for information regarding the reproduction and use of this thesis or dissertation.

School	Emory College
Department	Economics
Degree	BBA
Submission	Honors Thesis
Language	English
Research Field	Economics, Finance Economics, Theory
Keyword	Sharpe Diversification VIX Return Mutual Fund Model Asset Risk Optimization Markowitz
Committee Chair / Thesis Advisor	Luger, Richard, Emory University
Committee Members	Valerio III, Nicholas, Emory University Burdette, Allison, Emory University Maddox, Frank L, Emory University

Last modified

Primary PDF

Thumbnail	Title	Date Uploaded	Actions
	A Dynamic Optimization Model Incorporating the VIX Index to Predict Future Returns ()	2018-08-28 12:43:11 -0400	Press to Select an action Download

Supplemental Files

Thumbnail	Title	Date Uploaded	Actions