Despite the fact that volatility is at the center of activities in financial markets, the sample path realization of the volatility process is inherently unobservable. Numerous approaches are already utilized by both researchers and practitioners to determine volatility proxies. For example the traditional close-to-close estimator, the extreme-value estimator (range estimator), etc. A few scientists have discovered that the range estimator, which equals the difference between the daily highs and lows, is more efficient than a number of the more commonly adopted estimators.
Contents
CHAPTER 1. INTRODUCTION
1.1 BACKGROUND
1.2 MOTIVATION
1.3 MARKET
1.4 PRESENTATION OUTLINE
CHAPTER 2. LITERATURE REVIEW
2.1 LITERATURE ON THE RANGE-BASED ESTIMATORS
2.2 LITERATURE ON EXCHANGE RATE VOLATILITY FORECASTING
2.3 LITERATURE ON THE HISTORICAL VOLATILITY VS. IMPLIED VOLATILITY
CHAPTER 3. METHODOLOGY AND MODELING
3.1 METHODOLOGY AND TECHNIQUES AT THE ESTIMATION STAGE
3.1.1 Unit Root Test
3.1.2 Cointegration Analysis
3.2 MODEL BUILDING
3.2.1 Random walk model
3.2.2 ARIMA model
3.2.3 Vector Error-Correction Model
3.3 COMPARISON CRITERIA
3.3.1 MSE (Mean Squared Error)
3.3.2 MAD (Mean Absolute Deviation)
3.3.3 MDM test (Modified Diebold and Mariano test)
3.3.4 Direction of Change Test
CHAPTER 4. EMPIRICAL RESULTS
4.1 DATA
4.1.1 Data Description
4.1.2 Data Manipulation and Notation
4.1.3 Preliminary Analysis
4.2 SOME RESULTS AT THE ESTIMATION STAGE
4.2.1 Unit Root Test
4.2.2 Cointegration Test
4.2.3 Vector Error Correction Model
4.2.4 ARIMA Model
4.3 ACCURACY MEASURES
4.3.1 MSE and MAD as the criteria
4.3.2 MDM as the Criteria
4.3.3 Direction of Change as the Criterion
4.4 VARIANCE DECOMPOSITION
4.5 CONCLUDING REMARKS
APPENDIX 1: FIGURES IN CHAPTER 4
APPENDIX 2: TABLES IN CHAPTER 4
CHAPTER 5. CURRENCY OPTIONS AS AN ILLUSTRATIVE APPLICATION
5.1 OVERVIEW
5.2 DATA MANIPULATION
5.3 ACCURACY MEASURES
5.4 CONCLUDING REMARKS….
Source: City University of Hong Kong