Modeling the Asymmetry of Stock Movements Using Price Ranges Ray Y. Chou Academia Sinica “ The 2002 NTU International Finance Conference” Taipei. May 24-25,

Slides:



Advertisements
Similar presentations
Financial Econometrics
Advertisements

Scott Nelson July 29, Outline of Presentation Introduction to Quantitative Finance Time Series Concepts Stationarity, Autocorrelation, Time Series.
ARCH (Auto-Regressive Conditional Heteroscedasticity)
Mean, Proportion, CLT Bootstrap
1/19 Motivation Framework Data Regressions Portfolio Sorts Conclusion Option Returns and Individual Stock Volatility Jie Cao, Chinese University of Hong.
Estimating Value at Risk via Markov Switching ARCH models An Empirical Study on Stock Index Returns.
Juan P. Cajigas Centre for Econometric Analysis
Primbs, MS&E 345, Spring The Analysis of Volatility.
DYNAMIC CONDITIONAL CORRELATION : ECONOMETRIC RESULTS AND FINANCIAL APPLICATIONS Robert Engle New York University Prepared for CARLOS III, MAY 24, 2004.
LOGO Time Series technical analysis via new fast estimation methods Yan Jungang A E Huang Zhaokun A U Bai Ning A E.
HIA and Multi-Agent Models ●New paradigm of heterogeneous interacting agent models (Reviewed in Markose, Arifovic and Sunder (2007)) ●Zero intelligence.
AILEEN WANG PERIOD 5 An Analysis of Dynamic Applications of Black-Scholes.
1 Ka-fu Wong University of Hong Kong Volatility Measurement, Modeling, and Forecasting.
CAViaR : Conditional Value at Risk By Regression Quantiles Robert Engle and Simone Manganelli U.C.S.D. July 1999.
Bootstrap in Finance Esther Ruiz and Maria Rosa Nieto (A. Rodríguez, J. Romo and L. Pascual) Department of Statistics UNIVERSIDAD CARLOS III DE MADRID.
PREDICTABILITY OF NON- LINEAR TRADING RULES IN THE US STOCK MARKET CHONG & LAM 2010.
HDD and CDD Option Pricing with Market Price of Weather Risk for Taiwan Hung-Hsi Huang Yung-Ming Shiu Pei-Syun Lin The Journal of Futures Markets Vol.
The generalized Additive Nonparametric GARCH Model --With application to the Chinese stock market Ai Jun Hou Department of Economics School of Economics.
Forward-Looking Market Risk Premium Weiqi Zhang National University of Singapore Dec 2010.
Optimal Filtering of Jump Diffusions: Extracting Latent States from Asset Prices Jonathan Stroud, Wharton, U. Pennsylvania Stern-Wharton Conference on.
Multivariate volatility models Nimesh Mistry Filipp Levin.
Volatility Chapter 9 Risk Management and Financial Institutions 2e, Chapter 9, Copyright © John C. Hull
Nonlinear Filtering of Stochastic Volatility Aleksandar Zatezalo, University of Rijeka, Faculty of Philosophy in Rijeka, Rijeka, Croatia
Market Risk VaR: Historical Simulation Approach
1 CHAPTER 14 FORECASTING VOLATILITY II Figure 14.1 Autocorrelograms of the Squared Returns González-Rivera: Forecasting for Economics and Business, Copyright.
Volatility Spillovers and Asymmetry in Real Estate Stock Returns Kustrim Reka University of Geneva (Switzerland) Martin Hoesli University of Geneva (Switzerland),
1 Robert Engle UCSD and NYU July WHAT IS LIQUIDITY? n A market with low “transaction costs” including execution price, uncertainty and speed n.
+ Implied Volatility Index Kyu Won Choi March 2, 2011 Econ 201FS.
By: Brian Scott. Topics Defining a Stochastic Process Geometric Brownian Motion G.B.M. With Jump Diffusion G.B.M with jump diffusion when volatility is.
Single and Multiple Spell Discrete Time Hazards Models with Parametric and Non-Parametric Corrections for Unobserved Heterogeneity David K. Guilkey.
Kian Guan LIM and Christopher TING Singapore Management University
Risk Management and Financial Institutions 2e, Chapter 13, Copyright © John C. Hull 2009 Chapter 13 Market Risk VaR: Model- Building Approach 1.
Ewa Lukasik - Jakub Lawik - Juan Mojica - Xiaodong Xu.
Advanced Risk Management I Lecture 6 Non-linear portfolios.
Federico M. Bandi and Jeffrey R. Russell University of Chicago, Graduate School of Business.
1 Statistical Distribution Fitting Dr. Jason Merrick.
Downside Risk: Implications for Financial Management Robert Engle NYU Stern School of Business Tilburg April 22, 2004.
Chapter 16 Jones, Investments: Analysis and Management
Fundamentals of Futures and Options Markets, 5 th Edition, Copyright © John C. Hull Value at Risk Chapter 18.
Ray Y Chou Institute of Economics Academia Sinica
Value at Risk Chapter 16. The Question Being Asked in VaR “What loss level is such that we are X % confident it will not be exceeded in N business days?”
Forecasting Financial Volatilities with Extreme Values: The Conditional AutoRegressive Range (CARR) Model - JMCB (2005) Ray Y. Chou 周雨田 Academia Sinica,
Dissertation paper Modelling and Forecasting Volatility Index based on the stochastic volatility models MSc Student: LAVINIA-ROXANA DAVID Supervisor: Professor.
Robert Engle UCSD and NYU and Robert F. Engle, Econometric Services DYNAMIC CONDITIONAL CORRELATIONS.
Chapter 21 Principles of Corporate Finance Tenth Edition Valuing Options Slides by Matthew Will McGraw-Hill/Irwin Copyright © 2011 by the McGraw-Hill Companies,
NEW FRONTIERS FOR ARCH MODELS Prepared for Conference on Volatility Modeling and Forecasting Perth, Australia, September 2001 Robert Engle UCSD and NYU.
1. 2 EFFICIENT MARKET HYPOTHESIS n In its simplest form asserts that excess returns are unpredictable - possibly even by agents with special information.
Chapter 23 Volatility. Copyright © 2006 Pearson Addison-Wesley. All rights reserved Introduction Implied volatility Volatility estimation Volatility.
Run length and the Predictability of Stock Price Reversals Juan Yao Graham Partington Max Stevenson Finance Discipline, University of Sydney.
GARCH Models Þættir í fjármálum Verkefni 1-f Bjartur Logi Ye Shen
Patterns in the Jump Process, and the Relationship Between Jump Detection and Volatility Dynamics Matthew Rognlie Econ 201FS Wednesday, March 18, 2009.
Week 21 Order Statistics The order statistics of a set of random variables X 1, X 2,…, X n are the same random variables arranged in increasing order.
OPTIONS PRICING AND HEDGING WITH GARCH.THE PRICING KERNEL.HULL AND WHITE.THE PLUG-IN ESTIMATOR AND GARCH GAMMA.ENGLE-MUSTAFA – IMPLIED GARCH.DUAN AND EXTENSIONS.ENGLE.
Discussion of Mandelbrot Themes: Alpha (Tail Index) and Scaling (H) Prepared by Sheri Markose, Amadeo Alentorn and Vikentia Provizionatou WEHIA 2005 Implications.
13 – 1 Copyright © 2010 Pearson Education, Inc. Publishing as Prentice Hall. Forecasting 13 For Operations Management, 9e by Krajewski/Ritzman/Malhotra.
Week 21 Statistical Model A statistical model for some data is a set of distributions, one of which corresponds to the true unknown distribution that produced.
Kian Guan LIM and Christopher TING Singapore Management University
Predicting Returns and Volatilities with Ultra-High Frequency Data -
5. Volatility, sensitivity and VaR
Standard Errors Beside reporting a value of a point estimate we should consider some indication of its precision. For this we usually quote standard error.
Jump Detection and Analysis Investigation of Media/Telecomm Industry
Point and interval estimations of parameters of the normally up-diffused sign. Concept of statistical evaluation.
Ch8 Time Series Modeling
Market Risk VaR: Historical Simulation Approach
Simple Linear Regression - Introduction
Market Risk VaR: Model-Building Approach
Volatility Chapter 10.
Bootstrap - Example Suppose we have an estimator of a parameter and we want to express its accuracy by its standard error but its sampling distribution.
Applied Econometric Time Series Third Edition
Forecasting the daily dynamic hedge ratios in agricultural futures markets: evidence from the GARCH models Yuanyuan Zhang, School of Management, University.
Presentation transcript:

Modeling the Asymmetry of Stock Movements Using Price Ranges Ray Y. Chou Academia Sinica “ The 2002 NTU International Finance Conference” Taipei. May 24-25, 2002

Motivation Provide separate dynamic models for the upward- range and the downward-range to allow for asymmetries. Factors driving the upward movements and the downward movements maybe different. Upward range applications: market rallies, call options, historical new highs, limit order to sell Downward range applications: Value-at-Risk, put options, limit order to buy

Main Results ACARR is similar to CARR and ACD but with a different limiting distribution and with new interpretations and implications. Properties: QMLE, Distribution Empirical results using daily S&P500 index show asymmetry in dynamics, leverage effect, periodic patterns and interactions of upward and downward movements. Volatility forecast accuracy: ACARR>CARR>GARCH

Range as a measure of the “realized volatility” Simpler and more natural than the sum-squared- returns (measuring the integrated volatility) of Anderson et.al.(2000) Parkinson (1980) and others have established the efficiency gain of range over standard method in estimating volatilities Chou (2001) proposed CARR, a dynamic model for range with satisfactory performance

Discrete sampling from a continuous process

Upward range and downward range

Range and one-sided ranges

The Conditional Autoregressive Range Expectation (CARR) model in Chou (2001)

The Asymmetric Conditional Autoregressive Range Expectation -ACARR(p,q) model

Distribution assumptions in ACARR

ACARRX(p,q) – ACARR(p,q) with exogenous variables

Explanatory variables in the ACARRX(p,q) model Lagged returns – leverage effect Periodic (weekday) pattern Transaction volumes Interaction tems – lagged DWNR in expected UPR and lagged UPR in expected DWNR

Properties of ACARR Same as ACD of Engle and Russell (1998) but with a known limiting distribution for the error term A conditional mean model An asymmetric model for volatilities

Sources of asymmetry for an ACARRX(1,1) model  – short term shock impact  – long term persistence of shocks  – speed of mean-reverting  ‘s – effects of leverage, periodic pattern, interaction terms, among others

A special case of ACARR: Exponential ACARR(1,1) or EACARR(1,1) It’s useful to consider the exponential case for f(.), the distribution of the normalized range or the disturbance. Like GARCH models, a simple (p=1, q=1) specification works for many empirical examples.

ACARR vs. ACD identical formula ACARR Range data, positive valued, with fixed sample interval QMLE with EACARR Known limiting distribution A new volatility model ACD Duration data, positive valued, with non-fixed sample interval QMLE with EACD Unknown limiting distribution Hazard rate interpretation

The QMLE property Assuming any general density function f(.) for the disturbance term  t, the parameters in ACARR can be estimated consistently by estimating an exponential-ACARR model. Proof: see Engle and Russell (1998), p.1135

The QMLE Estimation Consistent standard errors are obtained by employing the robust covariance method in Bollerslev and Wooldridge (1987). See Engle and Russell (1998).

Empirical example: S&P500 daily index Sample period: 1962/01/03 – 2000/08/25 Data source: Yahoo.com Models used: EACARR(1,1), EACARRX(p,q) Both daily and weekly observations are used for estimation Forecast comparison of CARR and ACARR

Figure 11: Q-Q plot of et-DWNR

Extensions Robust ACARR – Interquartile range Multivariate ACARR Nonparametric or semiparametric ACARR Other data sets and simulations Long memory ACARR’s – IACARR, FIACARR,… ACARR and option price models

Conclusion ACARR is effective in modeling upward and downward market movements. Asymmetry found: dynamics, leverage effect, periodic patterns, interaction terms CARR provides more accurate volatility forecasts than GARCH (Chou (2001)) and ACARR gives further improvements.