FORECASTING VOLATILITY I

Slides:

Advertisements

Similar presentations

Cointegration and Error Correction Models

Advertisements

Dummy Variables. Introduction Discuss the use of dummy variables in Financial Econometrics. Examine the issue of normality and the use of dummy variables.

Chapter 3 Properties of Random Variables

Scott Nelson July 29, Outline of Presentation Introduction to Quantitative Finance Time Series Concepts Stationarity, Autocorrelation, Time Series.

Time Series Building 1. Model Identification

STAT 497 APPLIED TIME SERIES ANALYSIS

Primbs, MS&E 345, Spring The Analysis of Volatility.

1 Econ 240 C Lecture White noise inputoutput 1/(1 – z) White noise input output Random walkSynthesis 1/(1 – bz) White noise input output.

1 Econ 240 C Lecture Time Series Concepts Analysis and Synthesis.

Copyright © 2008 Pearson Education, Inc. Chapter 11 Probability and Calculus Copyright © 2008 Pearson Education, Inc.

1 Econ 240 C Lecture 3. 2 Time Series Concepts Analysis and Synthesis.

1 Ka-fu Wong University of Hong Kong Volatility Measurement, Modeling, and Forecasting.

QA-3 FRM-GARP Sep-2001 Zvi Wiener Quantitative Analysis 3.

Volatility Fin250f: Lecture 5.1 Fall 2005 Reading: Taylor, chapter 8.

FRM Zvi Wiener Following P. Jorion, Financial Risk Manager Handbook Financial Risk Management.

Volatility Chapter 9 Risk Management and Financial Institutions 2e, Chapter 9, Copyright © John C. Hull

1 CHAPTER 16 FORECASTING WITH NONLINEAR MODELS: AN INTRODUCTION Figure 16.1 Time Series of a SETAR Process with Two Regimes and Threshold Zero González-Rivera:

1 CHAPTER 14 FORECASTING VOLATILITY II Figure 14.1 Autocorrelograms of the Squared Returns González-Rivera: Forecasting for Economics and Business, Copyright.

© 2011 Pearson Education, Inc. Statistics for Business and Economics Chapter 13 Time Series: Descriptive Analyses, Models, & Forecasting.

Investments, 8 th edition Bodie, Kane and Marcus Slides by Susan Hine McGraw-Hill/Irwin Copyright © 2009 by The McGraw-Hill Companies, Inc. All rights.

McGraw-Hill/IrwinCopyright © 2009 by The McGraw-Hill Companies, Inc. All Rights Reserved. Chapter 7 Sampling Distributions.

Copyright © 2013 Pearson Education, Inc. Publishing as Prentice Hall Statistics for Business and Economics 8 th Edition Chapter 6 Sampling and Sampling.

Slide 1 Copyright © 2002 by O. Mikhail, Graphs are © by Pearson Education, Inc. Business Cycle Measurement Chapter 3.

Risks and Rates of Return

Requests for permission to make copies of any part of the work should be mailed to: Thomson/South-Western 5191 Natorp Blvd. Mason, OH Chapter 11.

Chapter 10 Capital Markets and the Pricing of Risk.

Copyright © 2011 by The McGraw-Hill Companies, Inc. All rights reserved. McGraw-Hill/Irwin Time Series Forecasting Chapter 16.

1 CHAPTER 3 STATISTICS AND TIME SERIES González-Rivera: Forecasting for Economics and Business, Copyright © 2013 Pearson Education, Inc. Figure 3.1 Examples.

1 CHAPTER 15 FINANCIAL APPLICATIONS OF TIME-VARYING VOLATILITY Figure 15.1 Value-at-Risk González-Rivera: Forecasting for Economics and Business, Copyright.

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?”

Estimating Volatilities and Correlations Chapter 21.

1 CHAPTER 13 FORECASTING VOLATILITY I Figure 13.1 The Forecasting Problem González-Rivera: Forecasting for Economics and Business, Copyright © 2013 Pearson.

Chapter 11 Risk and Rates of Return. Defining and Measuring Risk Risk is the chance that an unexpected outcome will occur A probability distribution is.

STAT 497 LECTURE NOTE 9 DIAGNOSTIC CHECKS 1. After identifying and estimating a time series model, the goodness-of-fit of the model and validity of the.

Chapter 23 Volatility. Copyright © 2006 Pearson Addison-Wesley. All rights reserved Introduction Implied volatility Volatility estimation Volatility.

Review of Probability. Important Topics 1 Random Variables and Probability Distributions 2 Expected Values, Mean, and Variance 3 Two Random Variables.

© K. Cuthbertson and D. Nitzsche Chapter 9 Measuring Asset Returns Investments.

1 Chapter 5 : Volatility Models Similar to linear regression analysis, many time series exhibit a non-constant variance (heteroscedasticity). In a regression.

1 CHAPTER 6 FORECASTING WITH MOVING AVERAGE (MA) MODELS González-Rivera: Forecasting for Economics and Business, Copyright © 2013 Pearson Education, Inc.

Estimating Volatilities and Correlations

Time Series Analysis PART II. Econometric Forecasting Forecasting is an important part of econometric analysis, for some people probably the most important.

Times Series Forecasting and Index Numbers Chapter 16 Copyright © 2014 by The McGraw-Hill Companies, Inc. All rights reserved.McGraw-Hill/Irwin.

Lecture 8 Stephen G. Hall ARCH and GARCH. REFS A thorough introduction ‘ARCH Models’ Bollerslev T, Engle R F and Nelson D B Handbook of Econometrics vol.

Analysis of financial data Anders Lundquist Spring 2010.

Forecasting. Model with indicator variables The choice of a forecasting technique depends on the components identified in the time series. The techniques.

Investments, 8 th edition Bodie, Kane and Marcus Slides by Susan Hine McGraw-Hill/Irwin Copyright © 2009 by The McGraw-Hill Companies, Inc. All rights.

Returns and stylized facts. Returns Objective: Use available information to say something about future returns.

Analysis of Financial Data Spring 2012 Lecture 9: Volatility Priyantha Wijayatunga Department of Statistics, Umeå University

Lecture 9 Forecasting. Introduction to Forecasting * * * * * * * * o o o o o o o o Model 1Model 2 Which model performs better? There are many forecasting.

Vera Tabakova, East Carolina University

Estimating Volatilities and Correlations

ARCH/GARCH Modelling of Exchange Rates in Turkey

Prediction, Goodness-of-Fit, and Modeling Issues

FORECASTING PRACTICE I

FORECASTING WITH A SYSTEM OF EQUATIONS: VECTOR AUTOREGRESSION

Elementary Statistics

STATIONARY AND NONSTATIONARY TIME SERIES

Volatility Chapter 10.

A LINK TO ECONOMIC MODELS

Chapter 4 Other Stationary Time Series Models

Financial Forecasting M.Sc. in Finance – 2018/19 – 1st Semester

Kunal Jain March 24, 2010 Economics 201FS

Introduction to Time Series

These slides are based on:

These slides are based on:

Diagnostics and Remedial Measures

Lecturer Dr. Veronika Alhanaqtah

Learning About Return and Risk from the Historical Record

Price Discovery BY Dhanya K A.

Presentation transcript:

FORECASTING VOLATILITY I CHAPTER 13 FORECASTING VOLATILITY I In ARMA models considered in this course we have assumed that volatility is constant But there is evidence that for some financial series volatility is time varying By volatility we mean variability: σ2, σ, MAD or other Figure 13.2 U.S. Real GDP with Volatility Bands These slides are based on: González-Rivera: Forecasting for Economics and Business, Copyright © 2013 Pearson Education, Inc. Slides adapted for this course. We thank Gloria González-Rivera and assume full responsibility for all errors due to our changes

Smoothed volatility estimate Figure 13.3 Volatility of Consumer Price Index Inflation Figure 13.4 Global Inflation Rate González-Rivera: Forecasting for Economics and Business, Copyright © 2013 Pearson Education, Inc.

Figure 13.5 Monthly Returns of the SP500 Index Table 13.1 Summary of the Dispersion in the Monthly Returns to the SP500 González-Rivera: Forecasting for Economics and Business, Copyright © 2013 Pearson Education, Inc.

13.3 Is There Time Dependence in Volatility? Figure 13.6 Time Series of SP500 Index, Yen/Dollar Exchange Rate, and 10-year Treasure Note Yield Table 13.2 Unit Root Testing: Value of the Dickey-Fuller Test The time series are nonstationary -> we proceed to take the first difference of each series (in logs) to get the returns rt González-Rivera: Forecasting for Economics and Business, Copyright © 2013 Pearson Education, Inc.

The series of returns does not display autocorrelation. Figure 13.7 Transformations of Weekly Returns to the SP500 Index and Their Autocorrelations The series of returns does not display autocorrelation. But the squared returns do. González-Rivera: Forecasting for Economics and Business, Copyright © 2013 Pearson Education, Inc.

Figure 13.7 Transformations of Weekly Returns to the SP500 Index and Their Autocorrelations González-Rivera: Forecasting for Economics and Business, Copyright © 2013 Pearson Education, Inc.

Figure 13.8 Transformations of Daily Returns to Yen/Dollar Exchange Rate and Their Autocorrelations González-Rivera: Forecasting for Economics and Business, Copyright © 2013 Pearson Education, Inc.

Figure 13.8 Transformations of Daily Returns to Yen/Dollar Exchange Rate and Their Autocorrelations González-Rivera: Forecasting for Economics and Business, Copyright © 2013 Pearson Education, Inc.

Figure 13.9 Transformations of Daily Returns to the 10-Year Treasury Notes and Their Autocorrelations González-Rivera: Forecasting for Economics and Business, Copyright © 2013 Pearson Education, Inc.

Volatility is time varying and exhibits time dependence. Figure 13.9 Transformations of Daily Returns to the 10-Year Treasury Notes and Their Autocorrelations Volatility is time varying and exhibits time dependence. As Mandelbrot (1963) pointed out: “large changes tend to be followed by large changes, of either sign, and small changes tend to be followed by small changes.” A phenomenon called “volatility clustering” González-Rivera: Forecasting for Economics and Business, Copyright © 2013 Pearson Education, Inc.

Not normally distributed: skewness (asymmetry) ≠ 0 Figure 13.10 Unconditional Histograms of SP500, Exchange Rate, and 10-Year Treasury Returns Not normally distributed: skewness (asymmetry) ≠ 0 kurtosis > 3 (heavy tails) Jarque-Bera test rejects Ho: Normal Returns are leptokurtic: they have fat tails, i.e., extreme events occur with large probability González-Rivera: Forecasting for Economics and Business, Copyright © 2013 Pearson Education, Inc.

Not normally distributed: skewness (asymmetry) ≠ 0 Figure 13.10 Unconditional Histograms of SP500,Exchange Rate,10-Year Treasury Returns (continued) NOW MUCH MORE: Not normally distributed: skewness (asymmetry) ≠ 0 kurtosis > 3 (heavy tails) Jarque-Bera test rejects Ho: Normal Volatility is strongly skewed to the right González-Rivera: Forecasting for Economics and Business, Copyright © 2013 Pearson Education, Inc.

Stylized facts of financial time series: Nonstationarity: Stock prices, exchange rates, interest rates, etc., have stochastic trends - unit root behavior; Returns are nearly uncorrelated: near to a white noise behavior; Returns have time varying-volatility; Volatility Clustering: large (small) movements tend to be followed by large (small) movements; Returns are non normally distributed (fat tails) : they are leptokurtic with kurtosis coefficient larger than 3; Asymmetry and Leverage effect: negative price movements (negative shocks) have a higher impact on volatility than positive surprises (positive shocks); González-Rivera: Forecasting for Economics and Business, Copyright © 2013 Pearson Education, Inc.

13.5.1 Rolling Window Volatility The estimator can be considered as a moving average in which all the components of the moving average have the same weight 1/n Figure 13.11 Rolling Window Volatility Forecast González-Rivera: Forecasting for Economics and Business, Copyright © 2013 Pearson Education, Inc.

13.5.2 Exponentially Weighted Moving Average (EWMA) Volatility If instead of equally weighting past squared realizations, we assign more weight to the most recent realizations, then we can define another estimator of the conditional variance as: When the sample size is large, this estimator can be approximated by the recursive formula: Of course, this is the EWMA: The exponential smoothing method Figure 13.12 EWMA Volatility Forecast González-Rivera: Forecasting for Economics and Business, Copyright © 2013 Pearson Education, Inc.