Multifractality. Theory and Evidence An Application to the Romanian Stock Market MSc Student: Cristina-Camelia Paduraru Supervisor: PhD Professor Moisa.

Slides:



Advertisements
Similar presentations
Fractals in Financial Markets
Advertisements

Ordinary least Squares
Chp.4 Lifetime Portfolio Selection Under Uncertainty
On the Mathematics and Economics Assumptions of Continuous-Time Models
COMM 472: Quantitative Analysis of Financial Decisions
Prediction, Goodness-of-Fit, and Modeling Issues ECON 6002 Econometrics Memorial University of Newfoundland Adapted from Vera Tabakova’s notes.
Introduction Data and simula- tion methodology VaR models and estimation results Estimation perfor- mance analysis Conclusions Appendix Doctoral School.
STAT 497 APPLIED TIME SERIES ANALYSIS
MGT 821/ECON 873 Volatility Smiles & Extension of Models
Zvi WienerContTimeFin - 1 slide 1 Financial Engineering Zvi Wiener tel:
1 17. Long Term Trends and Hurst Phenomena From ancient times the Nile river region has been known for its peculiar long-term behavior: long periods of.
Simple Linear Regression
LECTURE 9 : EMPRICIAL EVIDENCE : CAPM AND APT
Introduction to Financial Time Series From Ruey. S. Tsay’s slides.
Probing hadron-production processes by using new statistical methods to analyze data LIU Qin Department of Physics, CCNU, Wuhan, China.
McGraw-Hill/Irwin © 2008 The McGraw-Hill Companies, Inc., All Rights Reserved. Capital Asset Pricing and Arbitrage Pricing Theory CHAPTER 7.
Chapter 13 Stochastic Optimal Control The state of the system is represented by a controlled stochastic process. Section 13.2 formulates a stochastic optimal.
The Lognormal Distribution
Measuring market risk:
Elec471 Embedded Computer Systems Chapter 4, Probability and Statistics By Prof. Tim Johnson, PE Wentworth Institute of Technology Boston, MA Theory and.
Diffusion Processes and Ito’s Lemma
JUMP DIFFUSION MODELS Karina Mignone Option Pricing under Jump Diffusion.
Modelling and Detecting Long Memory in Stock Returns MSc student Ciprian Necula Doctoral School of Finance and Banking Academy of Economic Studies Bucharest.
Seiji Armstrong Huy Luong Huy Luong Alon Arad Alon Arad Kane Hill Kane Hill.
Jean-Paul Murara 25 th February 2009 Lappeenranta University of Technology.
Martingales Charles S. Tapiero. Martingales origins Its origin lies in the history of games of chance …. Girolamo Cardano proposed an elementary theory.
11.1 Options, Futures, and Other Derivatives, 4th Edition © 1999 by John C. Hull The Black-Scholes Model Chapter 11.
QA in Finance/ Ch 3 Probability in Finance Probability.
第四章 Brown运动和Ito公式.
Advanced Risk Management I Lecture 6 Non-linear portfolios.
Chapter 13 Wiener Processes and Itô’s Lemma
Federico M. Bandi and Jeffrey R. Russell University of Chicago, Graduate School of Business.
And, now take you into a WORLD of……………...
Comm W. Suo Slide 1. Comm W. Suo Slide 2 Diversification  Random selection  The effect of diversification  Markowitz diversification.
Presented By Dr. Paul Cottrell Company: Reykjavik.
Academy of Economic Studies DOCTORAL SCHOOL OF FINANCE AND BANKING Bucharest 2003 Long Memory in Volatility on the Romanian Stock Market Msc Student: Gabriel.
Chp.5 Optimum Consumption and Portfolio Rules in a Continuous Time Model Hai Lin Department of Finance, Xiamen University.
Borgan and Henderson:. Event History Methodology
Bodie Kane Marcus Perrakis RyanINVESTMENTS, Fourth Canadian Edition Chapter 10.
Actuarial Applications of Multifractal Modeling
1 4. Empirical distributions & prediction of returns 4.1 Prices and returns Price (P) ACF decays slowly. Log price: p = log(P) Single-period (rate of)
OTHER CORPORATE SECURITIES PREFERENCE SHARES Equity security that pays a (normally fixed) dividend. The issuer must pay the preference dividend before.
Prediction, Goodness-of-Fit, and Modeling Issues Prepared by Vera Tabakova, East Carolina University.
Lecture V Probability theory. Lecture questions Classical definition of probability Frequency probability Discrete variable and probability distribution.
Dissertation paper Modelling and Forecasting Volatility Index based on the stochastic volatility models MSc Student: LAVINIA-ROXANA DAVID Supervisor: Professor.
Academy of Economic Studies Doctoral School of Finance and Banking - DOFIN VOLATILITY AND LONG TERM RELATIONS IN EQUITY MARKETS : Empirical Evidence from.
Market Efficiency.
S TOCHASTIC M ODELS L ECTURE 4 P ART II B ROWNIAN M OTIONS Nan Chen MSc Program in Financial Engineering The Chinese University of Hong Kong (Shenzhen)
1 EE571 PART 3 Random Processes Huseyin Bilgekul Eeng571 Probability and astochastic Processes Department of Electrical and Electronic Engineering Eastern.
Risk Analysis Workshop April 14, 2004 HT, LRD and MF in teletraffic1 Heavy tails, long memory and multifractals in teletraffic modelling István Maricza.
The role of market impact and investor behavior on fund flows Yoni and Doyne 9/2/09.
Bodie Kane Marcus Perrakis RyanINVESTMENTS, Fourth Canadian Edition Copyright © McGraw-Hill Ryerson Limited, 2003 Slide 10-1 Chapter 10.
Discussion of Mandelbrot Themes: Alpha (Tail Index) and Scaling (H) Prepared by Sheri Markose, Amadeo Alentorn and Vikentia Provizionatou WEHIA 2005 Implications.
Chapter 13 Wiener Processes and Itô’s Lemma 1. Stochastic Processes Describes the way in which a variable such as a stock price, exchange rate or interest.
The Black-Scholes-Merton Model
CLT and Levy Stable Processes John Rundle Econophysics PHYS 250
Empirical Financial Economics
Capital Asset Pricing and Arbitrage Pricing Theory
Theory of Capital Markets
What Drives Firm-Level Stock Returns?
Asset Pricing and Skewness
Mathematical Finance An Introduction
Baosheng Yuan and Kan Chen
Dynamical Agents’ Strategies and the Fractal Market Hypothesis
Undergraduated Econometrics
Detection of financial crisis by methods of multifractal analysis
Brownian Motion & Itô Formula
Chapter 14 Wiener Processes and Itô’s Lemma
Chp.9 Option Pricing When Underlying Stock Returns are Discontinuous
Lecturer Dr. Veronika Alhanaqtah
Presentation transcript:

Multifractality. Theory and Evidence An Application to the Romanian Stock Market MSc Student: Cristina-Camelia Paduraru Supervisor: PhD Professor Moisa Altar

2 Presentation contents Motivation Review of the Literature Basics of Multifractal Modeling Methodology to Detect Multifractality Data Main Results Conclusions Bibliography

3 Motivation The major discrepancies between the Bachelier model and actual financial data: - long memory in the absolute values of returns - long tails relative to the Gaussian. The Multifractal Model of Asset Returns (MMAR) – Mandelbrot, Calvet, Fisher (1997) – accounts for these empirical regularities of financial time series and adds scale consistency.

4 Literature Review Mandelbrot, Calvet, Fisher (1997) – the MMAR is developed – the focus is on the scaling property: the moments of the returns scale as a power law of the time horizon. Calvet, Fisher, Mandelbrot (1997) – the focus is on the local properties of the multifractal processes. Fisher, Calvet, Mandelbrot (1997) – an empirical investigation of the MMAR – evidence of multifractality in Deutschemark/US Dollar currency exchange rates Calvet and Fisher (2002, 2008) – simplified version of the MMAR.

5 MMAR incorporates: fat (long) tails - Mandelbrot (1963), but the MMAR does not necessarily imply infinite variance. long dependence - fractional Brownian motion (FBM), Mandelbrot and Van Ness (1968). MMAR displays long dependence in the absolute value of price increments, while price increments themselves can be uncorrelated. the concept of trading time - Mandelbrot and Taylor (1967): explicit modeling of the relationship between unobserved natural time-scale of the returns process, and clock time.

6 Multifractal processes bridge the gap between Itô and Jump diffusions Itô diffusions - increments that grow locally at the rate (dt) 1/2 throughout their sample paths. FBM - local growth rates of order (dt) H, where H invariant over time (the Hurst exponent). Multifractals - a multiplicity of local growth rates for increments: (dt) α(t), where α(t) represents the Hölder exponent. Jump diffusions have α(t) = 0.

7 Construction of the MMAR Consider the price of a financial asset P(t) on [0, T] and the log-price process: 1. 2.θ(t) - the cumulative distribution function of a multifractal measure μ defined on [0, T]. 3. B H (t) and θ(t) are independent.

8 Under Conditions 1 – 3: X(t) - multifractal process with stationary increments; the moments of returns scale as a power law of the frequency of observation: as t→0. The scaling function τ X (q) - concave - has intercept τ X (0) = -1 Concavity of the scaling function => multifractality. Unifractal processes – linear scaling functions fully determined by H.

9 Hölder Exponent Let g be a function defined on the neighborhood of a given date t. The number, is called the Hölder exponent of g at t. Describes the local variability of the function at a point in time.

10 Multifractal Spectrum Describes the distribution of local Hölder exponents in a multifractal process. The multifractal spectrum f(α) is the Legendre transform of the scaling function τ (q). Between the spectrum of the log-price process and the spectrum of the trading time we have:

11 Testing for Multifractality log-price series Partitioning [0, T] into integer N intervals of length Δt, we define the partition function: X(t) – multifractal => the addends are identically distributed; the scaling law yields:, when the q th moment exists.

12 Taking logs: where. We plot logS q (Δt) vs log(Δt) for various values of q and Δt. Linearity of those functions => scaling. OLS estimations of the partition functions => τ X (q), the scaling function. Of particular interest: the value of q where This value of q identifies H:

13 The Scaling Function Calvet, Fisher, Mandelbrot (1997) shows that the scaling function - is concave - has intercept τ X (0) = -1 and From the scaling function we estimate the multifractal spectrum through the Legendre transform:

14 The Data High frequency data sets – all transaction prices with transaction time during the period Jan, 2007 – May, 2009 for four Romanian securities listed at the Bucharest Stock Exchange: SIF2, BRD, SNP and TEL. We have 328,555 transactions for SIF2 179,617 transactions for SNP 178,562 transactions for BRD 68,289 transactions for TEL.

15 Plots of the Partition Functions SIF2

16 Plots of the Partition Functions BRD

17 Plots of the Partition Functions SNP

18 Plots of the Partition Functions TEL

19 Plots of the Scaling Functions

20 Plots of the Scaling Functions

21 Plots of the Scaling Functions

22 Plots of the Scaling Functions

23 Plots of the Multifractal Spectrum

24 Plots of the Multifractal Spectrum

25 Plots of the Multifractal Spectrum

26 Plots of the Multifractal Spectrum

27 Main Results The partition functions – approximately linear => scaling in the moments of returns The scaling functions – concave => evidence for multifractality. Of particular interest: the value of q where This value of q identifies H: All scaling functions have intercept -1. Each of the scaling functions is asymptotically linear, with a slope approximately equal to α min. The minimum α corresponds to the most irregular instants on the price path, and thus the riskiest events for investors.

28 Main Results The multifractal spectrum is also concave and its maximum is approximately 1 in all of the four cases. The estimated multifractal spectrum: approximately quadratic => the limit lognormal multifractal measure for modeling the trading time. Calvet, Fisher, and Mandelbrot (1997)

29 Main Results We find: SIF2BRDSNPTEL

30 Conclusions We found evidence of multifractal scaling in 4 Romanian securities prices. Using a methodology based on scaling function and multifractal spectrum => we recovered the MMAR components. The estimated multifractal spectrum: approximately quadratic. We found slight persistence in the analyzed data. The scaling property holds from 4 days to one year. No intraday scaling! => We can model our series with multifractal processes at large time scales.

31 Bibliography Calvet, L.E., A.J. Fisher, and B.B. Mandelbrot (1997) “Large Deviations and the Distribution of Price Changes”, Cowles Foundation Discussion Paper No. 1165; Sauder School of Business Working Paper Calvet, L.E. and A.J. Fisher (1999), “A Multifractal Model of Assets Returns”, New York University Working Paper No. FIN Calvet, L.E. and A.J. Fisher (2002), “Multifractality in Asset Returns: Theory and Evidence”, Review of Economics and Statistics 84, Calvet, L.E. and A.J. Fisher (2008), “Multifractal Volatility: Theory, Forecasting, and Pricing”, Elsevier Fama, E.F. (1963), “Mandelbrot and the Stable Paretian Hypothesis”, Journal of Business 36, Fillol, J. (2003) "Multifractality: Theory and Evidence an Application to the French Stock Market", Economics Bulletin 3, 1−12 Fisher, A.J., L.E. Calvet, and B.B. Mandelbrot (1997), “Multifractality of Deutschemark / US Dollar Exchange Rates”, Cowles Foundation Discussion Paper No. 1166; Sauder School of Business Working Paper Mandelbrot, B.B. (1963), “The Variation of Certain Speculative Prices”, Journal of Business 36, Mandelbrot, B.B. (1967), “The Variation of the Prices of Cotton, Wheat, and Railroad Stocks, and of some Financial Rates”, Journal of Business 40,

32 Bibliography 2 Mandelbrot, B.B., and H.M. Taylor (1967), “On the Distribution of Stock Price Differences”, Operations Research 15, Mandelbrot, B.B., and J.W. Van Ness (1968), “Fractional Brownian Motions, Fractional Noises and Applications”, SIAM (Society for Industrial and Applied Mathematics) Review 10, Mandelbrot, B.B. (1972), “Possible refinement of the lognormal hypothesis concerning the distribution of energy dissipation in intermittent turbulence”, Statistical Models and Turbulence 12, Mandelbrot, B.B., A.J. Fisher, and L.E. Calvet (1997), “A Multifractal Model of Asset Returns”, Cowles Foundation Discussion Paper No. 1164; Sauder School of Business Working Paper Mandelbrot, B.B. (2001), “Scaling in Financial Prices: Tails and Dependence”, Quantitative Finance 1, Mandelbrot, B.B. (2001), “Scaling in Financial Prices: Multifractals and the Star Equation”, Quantitative Finance 1, Mandelbrot, B.B. (2001), “Scaling in Financial Prices: Cartoon Brownian Motions in Multifractal Time”, Quantitative Finance 1, Mandelbrot, B.B. (2001), “Scaling in Financial Prices: Multifractal Concentration”, Quantitative Finance 1, Mandelbrot, B.B., and Richard L. Hudson (2004), “The (mis) Behavior of Markets”, Basic Books