Testing Monotonicity of Pricing Kernels

Size: px
Start display at page:

Download "Testing Monotonicity of Pricing Kernels"

Transcription

1 Yuri Golubev Wolfgang Härdle Roman Timofeev C.A.S.E. Center for Applied Statistics and Economics Humboldt-Universität zu Berlin

2 Motivation 2-2 Motivation An investor observes the evolution of a stock price X t in the past and forms his subjective opinion about the future evolution of the price dax year Figure 1: DAX, Daily observations.

3 Motivation 2-3 Basic Notions X t half year DAX returns An opinion on the future value S t of the stock at time t can be described by a density function p which is called subjective density, a.k.a. historical density or physical density. Examples: Black-Scholes model (Nobel prize 1997): log normal distribution GARCH model (Nobel prize 23, Engle): stochastic volatility non-parametric diffusion model (Ait-Sahalia 2)

4 Motivation 2-4 Basic Notions Besides the subjective density there is also a state-price density (SPD) q for the stock price implied by the market prices of options, a.k.a. risk-neutral density. The state-price density differs from the subjective density because it corresponds to replication strategies (martingale risk neutral measure). A person alone does not use in general a replication strategy but thinks in terms of his subjective density.

5 Motivation 2-5 Utility Function and Pricing Kernel The pricing kernel (PK) K: K(s) = q(s) p(s) is proportional to Marginal Rate of Substitution (MRS): β U (X T ) U (X t) = exp( rt ) K(X T ) The form of the utility function U( ) is defined by a pricing kernel

6 Motivation 2-6 Is There a Bump? 6 Pricing kernel for Black Scholes Model Pricing kernel for June 25, Classical Concave Utility Function Market Utility for EPK on June 25,

7 Motivation 2-7 Statistical Setup For increasing sequence of returns X (k) such that X (1) X (2),..., X (n) we test if there exists any interval I, J such that the sequence K (k) = q(x (k)) p(x (k) ), I k J is not monotone decreasing having only q(x t ) as a known density

8 Motivation 2-8 Outline 1. Motivation 2. Basic Idea 3. ML Test for a Fixed Interval 4. Multiple Testing 5. Multiple Testing on Blocks 6. Simulations and Results 7. Conclusion

9 Basic Idea 3-1 Test Idea 1. Reduce the test problem using Pyke s order statistics theorem 2. Construct a likelihood ratio test for a nested (reduced) model for a fixed interval 3. Use intersection of tests to construct a test independent of intervals 4. Find critical values via Monte Carlo simulations 5. Test monotonicity of pricing kernel K

10 Basic Idea 3-2 Order Statistics Consider U 1,..., U n be i.i.d with a uniform distribution on [, 1]. For the order statistics define uniform spacings S k as U (1) U (2),..., U (n) S 1 = U (1) and S k = U (k) U (k 1)

11 Basic Idea 3-3 Pyke s Theorem Theorem Let U 1,..., U n be i.i.d with a uniform distribution on [, 1] and e 1,..., e n be i.i.d. standard exponentially distributed random variables. Then for uniform spacings S k { } L {S k, 1 k n} = L ek n i=1 e, 1 k n k Using the fact that E(e k ) = 1 we obtain the following result n { U (k) U (k 1) } = n Sk e k (1)

12 Basic Idea 3-4 Simplification Let P(x) be the cdf associated with the (historical) density p(x): Using Taylor approximation we can write P(x) = x p(u)du P ( X (k+1) ) = P ( X(k) ) + P ( X (k) ) ( X(k+1) X (k) ) U (k+1) U (k) = P(X (k+1) ) P(X (k) ) p(x (k) ) (X (k+1) X (k) ) (2)

13 Basic Idea 3-5 Simplification Combining (1) and (2) we obtain the simplification: n q(x (k) ) (X (k+1) X (k) ) q(x (k) ) p(x (k) ) e k = K k e k (3) Taking n q(x (k) ) (X (k+1) X (k) ) = Z(X(k) ) = Z k our problem is reduced to the following Check monotonicity of K(X (k) ) = K k using Z k = K k e k

14 MLT for a Fixed Interval 4-1 Testing Hypothesis for a Fixed Interval [I,J] Let A(I, J) be set of all positive decreasing sequences A(I, J) = {a k : a k a k+1, I k J} Hypothesis H : K A(I, J) and pricing kernel K(X k ) is monotone decreasing function Hypothesis H 1 : K is an arbitrary function

15 MLT for a Fixed Interval 4-2 Likelihood Ratio Test for a Fixed Interval [I,J] The monotonicity LRT is defined by the function: { } maxk A(I,J) {p(z, K)} φ(z) = 1 H α (I, J) max K {p(z, K)} where H α (I, J) is the critical value with significance level α. With h α (I, J) = log H α (I, J): { φ(z) = 1 log max } K A(I,J) {p(z, K)} h α (I, J) (4) max K {p(z, K)} H is rejected if φ(z) 1 and accepted if φ(z) = 1

16 MLT for a Fixed Interval 4-3 Computation of ML function Recall from equation (3) that Z k = K k e k. The likelihood function is: J Z k J log {p(z, K)} = log(k k ) (5) K k which gives us analytically: k=i k=i max K log {p(z, K)} = (J I ) J k=i log(z k)

17 MLT for a Fixed Interval 4-4 Computation of ML function Computation of max K A(I,J) log {p(z, K)} is performed with Newton-Raphson and projection on the decreasing sequence A(I, J). Search for the maximum likelihood over all possible monotone decreasing sequences by iterative optimization via the Newton Raphson algorithm. Isotonic regression over Z k parameters since Z k gives us max K log {p(z, K)}: max K A(I,J) log {p(z, K)} = J k=i Z k f iso (Z k ) J k=i log {f iso(z k )}

18 MLT for a Fixed Interval 4-5 Isotonic Regression and Newton Raphson Algorithm Initial Zs Optimal Isotonic Regression Figure 2: Isotonic Regression combined with Newton Rapshon algorithm

19 Multiple Testing 5-1 Likelihood Ratio Test for Multiple Intervals Construct a test which does not depend on intervals Typically solved with the help of tests intersection The hypothesis H of monotone decreasing function is refuted if φ(z) 1 at least on one of the intervals [I, J]. Look for a minimal critical surface h(i, J) such that: { P {min log max } } K A(I,J) p(z, r) h α (I, J) = α. I,J max K p(z, K)

20 Multiple Testing 5-2 Multiple Testing via Monte-Carlo Simulations Solution is extremely difficult and therefore Monte Carlo simulations are used to find a reasonable surface Generate the worst non-increasing case of the sequence K (k) as a constant: K (1) = K (2) =... = K (n) = 1 Then using the result that Z k = K k e k we generate Z k exp(1) as an i.i.d standard exponential random variable

21 Multiple Testing 5-3 Test Statistics Define ξ(i, J) as the log-lr with simulated Z k : ξ(i, J) = log max K A(I,J) p(z,k) max K p(z,k) Define mean M(I, J) and variance V 2 (I, J) of ξ(i, J): M(I, J) = E ξ(i, J) V 2 (I, J) = E [ ξ 2 (I, J) E ξ(i, J) ] 2 Parameters M(I, J) and V (I, J) are calculated by simulations.

22 Multiple Testing 5-4 Critical Surface The critical value t α is calculated via Monte-Carlo simulations: } P {min {ξ(i, J) M(I, J) + t αv (I, J)} = α (6) I,J Equation (6) gives us a corresponding critical surface h α (I, J) h α (I, J) = M(I, J) t α V (I, J)

23 Multiple Testing on Blocks 6-1 Introduction of Block Parameter Block parameter improves the power of the test by allowing the function to be monotone decreasing on interval of size b Instead of calculating ML for each point, we calculate it for averages of each block Block size b is a trade-off between the variance and the shift of test statistics distribution Test procedure successfully captures the shift of the cdf due to smaller variance

24 Multiple Testing on Blocks 6-2 Influence of Block Parameter 1.9 Initial and block tests distribution functions test distribution without block test distribution after block 1.9 Influence of block parameter b on cdf variance and shift b = 1 b = 5 b = cdf.5.4 Shift of cdf after increase of slope cdf Figure 3: Resulting Distributions after change of slope Figure 4: Influence of the block on shift and variance

25 Multiple Testing on Blocks 6-3 Influence of Block Parameter For small size block distribution is shifted, but variance is also big For large blocks the distribution function is less shifted but has smaller variance Block size b = 1 corresponds to no block We test for different b in order to increase the power of the test

26 Multiple Testing on Blocks 6-4 Test with Block Parameter Test statistics ξ(i, J, b) is obtained as an average for each block, where m is a number of blocks: m ( max log {p(z, K)} = m j b k=j b b+1 log Z ) k K b H hypothesis is refuted when monotonicity is rejected at least on one of the intervals I, J with any block size b: { min ξ(i, J, b) M(I, J, b) + tα,b V (I, J, b) } (7) (I,J,b) j=1

27 Multiple Testing on Blocks 6-5 Test Summary 1. Compute Z(X (k) ) = n q(x (k) ) {X (k+1) X (k) } 2. Compute test statistics ξ(i, J, b) = log max K A(I,J) p(z,k) max K p(z,k) = max K A(I,J) log {p(z, K)} max K log {p(z, K)} 3. Take decision: if { ξ(i, J, b) M(I, J, b) + tα,b V (I, J, b) } min I,J,b then K( ) is a non-monotone decreasing function

28 Applications and Simulations 7-1 Real Z k 9 Calculated Z(k) values for June 3th Zs Dax returns Figure 5: Calculated Z k and optimized isotonic regression over DAX returns data in 22

29 Applications and Simulations 7-2 Simulated surfaces M(I, J, b) and V (I, J, b) M(I,J) surface for n=255 V(I,J) surface for n= M(I,J) 6 8 V(I,J) I J I J Figure 6: Simulated surface M(I, J, b) with Monte-Carlo method for n = 255 and b = 1 Figure 7: Simulated surface V (I, J, b) with Monte-Carlo method for n = 255 and b = 1

30 Applications and Simulations 7-3 Simulated t α,b 7 5% and 1% critival values for different b parameters 5% crit. values 1% crit. values Crit. Value b Figure 8: Distribution of critical values t.5,b and t.1,b over block parameter b

31 Applications and Simulations 7-4 Test surface ξ(i, J, b) M(I, J, b) + t α V (I, J, b) Testing surface ξ(i,j) M(I,J)+ t.5 V and Zero surface Testing surface ξ(i,j) M(I,J)+ t.5 V and Zero surface 5 5 ξ(i,j M(I,J) + t α V) ξ(i,j M(I,J) + t α V) I J I J Figure 9: Testing surfaces for year 22, α = 5% and b = 5 Figure 1: Testing surfaces for year 24, α = 5% and b = 5

32 Conclusion 8-1 Obtained results for EPK in 2, 22 and 24 Sign. level/year of analysis % Significance level min I,J,b Accepted H H H 1 H 1% Significance level min I,J,b Accepted H 1 H 1 H 1 H Table 1: Summary of results on monotonicity of EPK in 2, 22 and 24.

33 Conclusion 8-2 Conclusion We constructed a test which allows to verify monotonicity of PKs Strictly decreasing PKs correspond to concave utility functions and vice versa Introduction of block parameter significantly improved the power of the test We found the evidence of non-monotone EPKs for DAX in 2 and 22 Test findings suggest that PK structure may change over time

34 Conclusion 8-3 References Ait-Sahalia, Y. and Lo, A. (2) Nonparametric risk management and implied risk aversion, Journal of Econometrics 94(1-2), Giacomini, E., Handel, M. and Härdle, W. (26) Time Dependent Relative Risk Aversion, proceedings, 9th Karlsruhe Econometrics Workshop 26. Jackwerth, J. C. (22) Recovering Risk Aversion from Option Prices and Realized Returns, Review of Financial Studies, 13, Pyke, R. (1965) Spacings, J.R. Statistical Society, B 27,

Time Varying Hierarchical Archimedean Copulae (HALOC)

Time Varying Hierarchical Archimedean Copulae (HALOC) Time Varying Hierarchical Archimedean Copulae () Wolfgang Härdle Ostap Okhrin Yarema Okhrin Ladislaus von Bortkiewicz Chair of Statistics C.A.S.E. Center for Applied Statistics and Economics Humboldt-Universität

More information

ECONOMICS 7200 MODERN TIME SERIES ANALYSIS Econometric Theory and Applications

ECONOMICS 7200 MODERN TIME SERIES ANALYSIS Econometric Theory and Applications ECONOMICS 7200 MODERN TIME SERIES ANALYSIS Econometric Theory and Applications Yongmiao Hong Department of Economics & Department of Statistical Sciences Cornell University Spring 2019 Time and uncertainty

More information

Probabilities & Statistics Revision

Probabilities & Statistics Revision Probabilities & Statistics Revision Christopher Ting Christopher Ting http://www.mysmu.edu/faculty/christophert/ : christopherting@smu.edu.sg : 6828 0364 : LKCSB 5036 January 6, 2017 Christopher Ting QF

More information

13. Estimation and Extensions in the ARCH model. MA6622, Ernesto Mordecki, CityU, HK, References for this Lecture:

13. Estimation and Extensions in the ARCH model. MA6622, Ernesto Mordecki, CityU, HK, References for this Lecture: 13. Estimation and Extensions in the ARCH model MA6622, Ernesto Mordecki, CityU, HK, 2006. References for this Lecture: Robert F. Engle. GARCH 101: The Use of ARCH/GARCH Models in Applied Econometrics,

More information

Volatility. Gerald P. Dwyer. February Clemson University

Volatility. Gerald P. Dwyer. February Clemson University Volatility Gerald P. Dwyer Clemson University February 2016 Outline 1 Volatility Characteristics of Time Series Heteroskedasticity Simpler Estimation Strategies Exponentially Weighted Moving Average Use

More information

GARCH Models. Eduardo Rossi University of Pavia. December Rossi GARCH Financial Econometrics / 50

GARCH Models. Eduardo Rossi University of Pavia. December Rossi GARCH Financial Econometrics / 50 GARCH Models Eduardo Rossi University of Pavia December 013 Rossi GARCH Financial Econometrics - 013 1 / 50 Outline 1 Stylized Facts ARCH model: definition 3 GARCH model 4 EGARCH 5 Asymmetric Models 6

More information

Determining and Forecasting High-Frequency Value-at-Risk by Using Lévy Processes

Determining and Forecasting High-Frequency Value-at-Risk by Using Lévy Processes Determining and Forecasting High-Frequency Value-at-Risk by Using Lévy Processes W ei Sun 1, Svetlozar Rachev 1,2, F rank J. F abozzi 3 1 Institute of Statistics and Mathematical Economics, University

More information

Bayesian estimation of bandwidths for a nonparametric regression model with a flexible error density

Bayesian estimation of bandwidths for a nonparametric regression model with a flexible error density ISSN 1440-771X Australia Department of Econometrics and Business Statistics http://www.buseco.monash.edu.au/depts/ebs/pubs/wpapers/ Bayesian estimation of bandwidths for a nonparametric regression model

More information

Dynamic Risk Measures and Nonlinear Expectations with Markov Chain noise

Dynamic Risk Measures and Nonlinear Expectations with Markov Chain noise Dynamic Risk Measures and Nonlinear Expectations with Markov Chain noise Robert J. Elliott 1 Samuel N. Cohen 2 1 Department of Commerce, University of South Australia 2 Mathematical Insitute, University

More information

Research Statement. Zhongwen Liang

Research Statement. Zhongwen Liang Research Statement Zhongwen Liang My research is concentrated on theoretical and empirical econometrics, with the focus of developing statistical methods and tools to do the quantitative analysis of empirical

More information

Model estimation through matrix equations in financial econometrics

Model estimation through matrix equations in financial econometrics Model estimation through matrix equations in financial econometrics Federico Poloni 1 Joint work with Giacomo Sbrana 2 1 Technische Universität Berlin (A. Von Humboldt postdoctoral fellow) 2 Rouen Business

More information

Model Specification Testing in Nonparametric and Semiparametric Time Series Econometrics. Jiti Gao

Model Specification Testing in Nonparametric and Semiparametric Time Series Econometrics. Jiti Gao Model Specification Testing in Nonparametric and Semiparametric Time Series Econometrics Jiti Gao Department of Statistics School of Mathematics and Statistics The University of Western Australia Crawley

More information

Computer Vision Group Prof. Daniel Cremers. 10a. Markov Chain Monte Carlo

Computer Vision Group Prof. Daniel Cremers. 10a. Markov Chain Monte Carlo Group Prof. Daniel Cremers 10a. Markov Chain Monte Carlo Markov Chain Monte Carlo In high-dimensional spaces, rejection sampling and importance sampling are very inefficient An alternative is Markov Chain

More information

Econ 423 Lecture Notes: Additional Topics in Time Series 1

Econ 423 Lecture Notes: Additional Topics in Time Series 1 Econ 423 Lecture Notes: Additional Topics in Time Series 1 John C. Chao April 25, 2017 1 These notes are based in large part on Chapter 16 of Stock and Watson (2011). They are for instructional purposes

More information

Motivation Non-linear Rational Expectations The Permanent Income Hypothesis The Log of Gravity Non-linear IV Estimation Summary.

Motivation Non-linear Rational Expectations The Permanent Income Hypothesis The Log of Gravity Non-linear IV Estimation Summary. Econometrics I Department of Economics Universidad Carlos III de Madrid Master in Industrial Economics and Markets Outline Motivation 1 Motivation 2 3 4 5 Motivation Hansen's contributions GMM was developed

More information

Vladimir Spokoiny Foundations and Applications of Modern Nonparametric Statistics

Vladimir Spokoiny Foundations and Applications of Modern Nonparametric Statistics W eierstraß-institut für Angew andte Analysis und Stochastik Vladimir Spokoiny Foundations and Applications of Modern Nonparametric Statistics Mohrenstr. 39, 10117 Berlin spokoiny@wias-berlin.de www.wias-berlin.de/spokoiny

More information

Recovering Copulae from Conditional Quantiles

Recovering Copulae from Conditional Quantiles Wolfgang K. Härdle Chen Huang Alexander Ristig Ladislaus von Bortkiewicz Chair of Statistics C.A.S.E. Center for Applied Statistics and Economics HumboldtUniversität zu Berlin http://lvb.wiwi.hu-berlin.de

More information

Generated Covariates in Nonparametric Estimation: A Short Review.

Generated Covariates in Nonparametric Estimation: A Short Review. Generated Covariates in Nonparametric Estimation: A Short Review. Enno Mammen, Christoph Rothe, and Melanie Schienle Abstract In many applications, covariates are not observed but have to be estimated

More information

A nonparametric method of multi-step ahead forecasting in diffusion processes

A nonparametric method of multi-step ahead forecasting in diffusion processes A nonparametric method of multi-step ahead forecasting in diffusion processes Mariko Yamamura a, Isao Shoji b a School of Pharmacy, Kitasato University, Minato-ku, Tokyo, 108-8641, Japan. b Graduate School

More information

Bayesian Semiparametric GARCH Models

Bayesian Semiparametric GARCH Models Bayesian Semiparametric GARCH Models Xibin (Bill) Zhang and Maxwell L. King Department of Econometrics and Business Statistics Faculty of Business and Economics xibin.zhang@monash.edu Quantitative Methods

More information

Department of Economics, Vanderbilt University While it is known that pseudo-out-of-sample methods are not optimal for

Department of Economics, Vanderbilt University While it is known that pseudo-out-of-sample methods are not optimal for Comment Atsushi Inoue Department of Economics, Vanderbilt University (atsushi.inoue@vanderbilt.edu) While it is known that pseudo-out-of-sample methods are not optimal for comparing models, they are nevertheless

More information

Multivariate GARCH models.

Multivariate GARCH models. Multivariate GARCH models. Financial market volatility moves together over time across assets and markets. Recognizing this commonality through a multivariate modeling framework leads to obvious gains

More information

Bayesian Semiparametric GARCH Models

Bayesian Semiparametric GARCH Models Bayesian Semiparametric GARCH Models Xibin (Bill) Zhang and Maxwell L. King Department of Econometrics and Business Statistics Faculty of Business and Economics xibin.zhang@monash.edu Quantitative Methods

More information

Review. DS GA 1002 Statistical and Mathematical Models. Carlos Fernandez-Granda

Review. DS GA 1002 Statistical and Mathematical Models.   Carlos Fernandez-Granda Review DS GA 1002 Statistical and Mathematical Models http://www.cims.nyu.edu/~cfgranda/pages/dsga1002_fall16 Carlos Fernandez-Granda Probability and statistics Probability: Framework for dealing with

More information

Gaussian kernel GARCH models

Gaussian kernel GARCH models Gaussian kernel GARCH models Xibin (Bill) Zhang and Maxwell L. King Department of Econometrics and Business Statistics Faculty of Business and Economics 7 June 2013 Motivation A regression model is often

More information

Modeling Ultra-High-Frequency Multivariate Financial Data by Monte Carlo Simulation Methods

Modeling Ultra-High-Frequency Multivariate Financial Data by Monte Carlo Simulation Methods Outline Modeling Ultra-High-Frequency Multivariate Financial Data by Monte Carlo Simulation Methods Ph.D. Student: Supervisor: Marco Minozzo Dipartimento di Scienze Economiche Università degli Studi di

More information

Markov Chain Monte Carlo

Markov Chain Monte Carlo 1 Motivation 1.1 Bayesian Learning Markov Chain Monte Carlo Yale Chang In Bayesian learning, given data X, we make assumptions on the generative process of X by introducing hidden variables Z: p(z): prior

More information

Short Questions (Do two out of three) 15 points each

Short Questions (Do two out of three) 15 points each Econometrics Short Questions Do two out of three) 5 points each ) Let y = Xβ + u and Z be a set of instruments for X When we estimate β with OLS we project y onto the space spanned by X along a path orthogonal

More information

Do Markov-Switching Models Capture Nonlinearities in the Data? Tests using Nonparametric Methods

Do Markov-Switching Models Capture Nonlinearities in the Data? Tests using Nonparametric Methods Do Markov-Switching Models Capture Nonlinearities in the Data? Tests using Nonparametric Methods Robert V. Breunig Centre for Economic Policy Research, Research School of Social Sciences and School of

More information

A Specification Test for Time Series Models by a Normality Transformation

A Specification Test for Time Series Models by a Normality Transformation A Specification Test for Time Series Models by a Normality Transformation Jin-Chuan Duan (First Draft: May 2003 (This Draft: Oct 2003 Abstract A correctly specified time series model can be used to transform

More information

The Instability of Correlations: Measurement and the Implications for Market Risk

The Instability of Correlations: Measurement and the Implications for Market Risk The Instability of Correlations: Measurement and the Implications for Market Risk Prof. Massimo Guidolin 20254 Advanced Quantitative Methods for Asset Pricing and Structuring Winter/Spring 2018 Threshold

More information

Introduction to Algorithmic Trading Strategies Lecture 10

Introduction to Algorithmic Trading Strategies Lecture 10 Introduction to Algorithmic Trading Strategies Lecture 10 Risk Management Haksun Li haksun.li@numericalmethod.com www.numericalmethod.com Outline Value at Risk (VaR) Extreme Value Theory (EVT) References

More information

Graduate Econometrics I: What is econometrics?

Graduate Econometrics I: What is econometrics? Graduate Econometrics I: What is econometrics? Yves Dominicy Université libre de Bruxelles Solvay Brussels School of Economics and Management ECARES Yves Dominicy Graduate Econometrics I: What is econometrics?

More information

Machine learning, shrinkage estimation, and economic theory

Machine learning, shrinkage estimation, and economic theory Machine learning, shrinkage estimation, and economic theory Maximilian Kasy December 14, 2018 1 / 43 Introduction Recent years saw a boom of machine learning methods. Impressive advances in domains such

More information

Monte Carlo Composition Inversion Acceptance/Rejection Sampling. Direct Simulation. Econ 690. Purdue University

Monte Carlo Composition Inversion Acceptance/Rejection Sampling. Direct Simulation. Econ 690. Purdue University Methods Econ 690 Purdue University Outline 1 Monte Carlo Integration 2 The Method of Composition 3 The Method of Inversion 4 Acceptance/Rejection Sampling Monte Carlo Integration Suppose you wish to calculate

More information

A Modified Fractionally Co-integrated VAR for Predicting Returns

A Modified Fractionally Co-integrated VAR for Predicting Returns A Modified Fractionally Co-integrated VAR for Predicting Returns Xingzhi Yao Marwan Izzeldin Department of Economics, Lancaster University 13 December 215 Yao & Izzeldin (Lancaster University) CFE (215)

More information

EC4051 Project and Introductory Econometrics

EC4051 Project and Introductory Econometrics EC4051 Project and Introductory Econometrics Dudley Cooke Trinity College Dublin Dudley Cooke (Trinity College Dublin) Intro to Econometrics 1 / 23 Project Guidelines Each student is required to undertake

More information

Introduction to Machine Learning CMU-10701

Introduction to Machine Learning CMU-10701 Introduction to Machine Learning CMU-10701 Markov Chain Monte Carlo Methods Barnabás Póczos & Aarti Singh Contents Markov Chain Monte Carlo Methods Goal & Motivation Sampling Rejection Importance Markov

More information

SFB 823. A simple and focused backtest of value at risk. Discussion Paper. Walter Krämer, Dominik Wied

SFB 823. A simple and focused backtest of value at risk. Discussion Paper. Walter Krämer, Dominik Wied SFB 823 A simple and focused backtest of value at risk Discussion Paper Walter Krämer, Dominik Wied Nr. 17/2015 A simple and focused backtest of value at risk 1 by Walter Krämer and Dominik Wied Fakultät

More information

Shape of the return probability density function and extreme value statistics

Shape of the return probability density function and extreme value statistics Shape of the return probability density function and extreme value statistics 13/09/03 Int. Workshop on Risk and Regulation, Budapest Overview I aim to elucidate a relation between one field of research

More information

Marginal Specifications and a Gaussian Copula Estimation

Marginal Specifications and a Gaussian Copula Estimation Marginal Specifications and a Gaussian Copula Estimation Kazim Azam Abstract Multivariate analysis involving random variables of different type like count, continuous or mixture of both is frequently required

More information

Financial Econometrics

Financial Econometrics Financial Econometrics Nonlinear time series analysis Gerald P. Dwyer Trinity College, Dublin January 2016 Outline 1 Nonlinearity Does nonlinearity matter? Nonlinear models Tests for nonlinearity Forecasting

More information

Volatility, Information Feedback and Market Microstructure Noise: A Tale of Two Regimes

Volatility, Information Feedback and Market Microstructure Noise: A Tale of Two Regimes Volatility, Information Feedback and Market Microstructure Noise: A Tale of Two Regimes Torben G. Andersen Northwestern University Gökhan Cebiroglu University of Vienna Nikolaus Hautsch University of Vienna

More information

Local Quantile Regression

Local Quantile Regression Wolfgang K. Härdle Vladimir Spokoiny Weining Wang Ladislaus von Bortkiewicz Chair of Statistics C.A.S.E. - Center for Applied Statistics and Economics Humboldt-Universität zu Berlin http://ise.wiwi.hu-berlin.de

More information

Fractals. Mandelbrot defines a fractal set as one in which the fractal dimension is strictly greater than the topological dimension.

Fractals. Mandelbrot defines a fractal set as one in which the fractal dimension is strictly greater than the topological dimension. Fractals Fractals are unusual, imperfectly defined, mathematical objects that observe self-similarity, that the parts are somehow self-similar to the whole. This self-similarity process implies that fractals

More information

A Brief Introduction to Intersection-Union Tests. Jimmy Akira Doi. North Carolina State University Department of Statistics

A Brief Introduction to Intersection-Union Tests. Jimmy Akira Doi. North Carolina State University Department of Statistics Introduction A Brief Introduction to Intersection-Union Tests Often, the quality of a product is determined by several parameters. The product is determined to be acceptable if each of the parameters meets

More information

Location Multiplicative Error Model. Asymptotic Inference and Empirical Analysis

Location Multiplicative Error Model. Asymptotic Inference and Empirical Analysis : Asymptotic Inference and Empirical Analysis Qian Li Department of Mathematics and Statistics University of Missouri-Kansas City ql35d@mail.umkc.edu October 29, 2015 Outline of Topics Introduction GARCH

More information

A Semi-Parametric Measure for Systemic Risk

A Semi-Parametric Measure for Systemic Risk Natalia Sirotko-Sibirskaya Ladislaus von Bortkiewicz Chair of Statistics C.A.S.E. - Center for Applied Statistics and Economics Humboldt Universität zu Berlin http://lvb.wiwi.hu-berlin.de http://www.case.hu-berlin.de

More information

1: PROBABILITY REVIEW

1: PROBABILITY REVIEW 1: PROBABILITY REVIEW Marek Rutkowski School of Mathematics and Statistics University of Sydney Semester 2, 2016 M. Rutkowski (USydney) Slides 1: Probability Review 1 / 56 Outline We will review the following

More information

Computer Vision Group Prof. Daniel Cremers. 11. Sampling Methods

Computer Vision Group Prof. Daniel Cremers. 11. Sampling Methods Prof. Daniel Cremers 11. Sampling Methods Sampling Methods Sampling Methods are widely used in Computer Science as an approximation of a deterministic algorithm to represent uncertainty without a parametric

More information

Midterm exam CS 189/289, Fall 2015

Midterm exam CS 189/289, Fall 2015 Midterm exam CS 189/289, Fall 2015 You have 80 minutes for the exam. Total 100 points: 1. True/False: 36 points (18 questions, 2 points each). 2. Multiple-choice questions: 24 points (8 questions, 3 points

More information

Robustness to Parametric Assumptions in Missing Data Models

Robustness to Parametric Assumptions in Missing Data Models Robustness to Parametric Assumptions in Missing Data Models Bryan Graham NYU Keisuke Hirano University of Arizona April 2011 Motivation Motivation We consider the classic missing data problem. In practice

More information

6. The econometrics of Financial Markets: Empirical Analysis of Financial Time Series. MA6622, Ernesto Mordecki, CityU, HK, 2006.

6. The econometrics of Financial Markets: Empirical Analysis of Financial Time Series. MA6622, Ernesto Mordecki, CityU, HK, 2006. 6. The econometrics of Financial Markets: Empirical Analysis of Financial Time Series MA6622, Ernesto Mordecki, CityU, HK, 2006. References for Lecture 5: Quantitative Risk Management. A. McNeil, R. Frey,

More information

Discrete Dependent Variable Models

Discrete Dependent Variable Models Discrete Dependent Variable Models James J. Heckman University of Chicago This draft, April 10, 2006 Here s the general approach of this lecture: Economic model Decision rule (e.g. utility maximization)

More information

Trajectorial Martingales, Null Sets, Convergence and Integration

Trajectorial Martingales, Null Sets, Convergence and Integration Trajectorial Martingales, Null Sets, Convergence and Integration Sebastian Ferrando, Department of Mathematics, Ryerson University, Toronto, Canada Alfredo Gonzalez and Sebastian Ferrando Trajectorial

More information

Computer Intensive Methods in Mathematical Statistics

Computer Intensive Methods in Mathematical Statistics Computer Intensive Methods in Mathematical Statistics Department of mathematics johawes@kth.se Lecture 5 Sequential Monte Carlo methods I 31 March 2017 Computer Intensive Methods (1) Plan of today s lecture

More information

Financial Econometrics Return Predictability

Financial Econometrics Return Predictability Financial Econometrics Return Predictability Eric Zivot March 30, 2011 Lecture Outline Market Efficiency The Forms of the Random Walk Hypothesis Testing the Random Walk Hypothesis Reading FMUND, chapter

More information

Bias Variance Trade-off

Bias Variance Trade-off Bias Variance Trade-off The mean squared error of an estimator MSE(ˆθ) = E([ˆθ θ] 2 ) Can be re-expressed MSE(ˆθ) = Var(ˆθ) + (B(ˆθ) 2 ) MSE = VAR + BIAS 2 Proof MSE(ˆθ) = E((ˆθ θ) 2 ) = E(([ˆθ E(ˆθ)]

More information

CPSC 540: Machine Learning

CPSC 540: Machine Learning CPSC 540: Machine Learning MCMC and Non-Parametric Bayes Mark Schmidt University of British Columbia Winter 2016 Admin I went through project proposals: Some of you got a message on Piazza. No news is

More information

MFE Financial Econometrics 2018 Final Exam Model Solutions

MFE Financial Econometrics 2018 Final Exam Model Solutions MFE Financial Econometrics 2018 Final Exam Model Solutions Tuesday 12 th March, 2019 1. If (X, ε) N (0, I 2 ) what is the distribution of Y = µ + β X + ε? Y N ( µ, β 2 + 1 ) 2. What is the Cramer-Rao lower

More information

Final Exam Financial Data Analysis at the University of Freiburg (Winter Semester 2008/2009) Friday, November 14, 2008,

Final Exam Financial Data Analysis at the University of Freiburg (Winter Semester 2008/2009) Friday, November 14, 2008, Professor Dr. Roman Liesenfeld Final Exam Financial Data Analysis at the University of Freiburg (Winter Semester 2008/2009) Friday, November 14, 2008, 10.00 11.30am 1 Part 1 (38 Points) Consider the following

More information

Unified Discrete-Time and Continuous-Time Models. and High-Frequency Financial Data

Unified Discrete-Time and Continuous-Time Models. and High-Frequency Financial Data Unified Discrete-Time and Continuous-Time Models and Statistical Inferences for Merged Low-Frequency and High-Frequency Financial Data Donggyu Kim and Yazhen Wang University of Wisconsin-Madison December

More information

Bootstrap tests of multiple inequality restrictions on variance ratios

Bootstrap tests of multiple inequality restrictions on variance ratios Economics Letters 91 (2006) 343 348 www.elsevier.com/locate/econbase Bootstrap tests of multiple inequality restrictions on variance ratios Jeff Fleming a, Chris Kirby b, *, Barbara Ostdiek a a Jones Graduate

More information

Choice Under Uncertainty

Choice Under Uncertainty Choice Under Uncertainty Z a finite set of outcomes. P the set of probabilities on Z. p P is (p 1,...,p n ) with each p i 0 and n i=1 p i = 1 Binary relation on P. Objective probability case. Decision

More information

Sample Exam Questions for Econometrics

Sample Exam Questions for Econometrics Sample Exam Questions for Econometrics 1 a) What is meant by marginalisation and conditioning in the process of model reduction within the dynamic modelling tradition? (30%) b) Having derived a model for

More information

Introduction to Regression Analysis. Dr. Devlina Chatterjee 11 th August, 2017

Introduction to Regression Analysis. Dr. Devlina Chatterjee 11 th August, 2017 Introduction to Regression Analysis Dr. Devlina Chatterjee 11 th August, 2017 What is regression analysis? Regression analysis is a statistical technique for studying linear relationships. One dependent

More information

ECON4515 Finance theory 1 Diderik Lund, 5 May Perold: The CAPM

ECON4515 Finance theory 1 Diderik Lund, 5 May Perold: The CAPM Perold: The CAPM Perold starts with a historical background, the development of portfolio theory and the CAPM. Points out that until 1950 there was no theory to describe the equilibrium determination of

More information

Time Series Models for Measuring Market Risk

Time Series Models for Measuring Market Risk Time Series Models for Measuring Market Risk José Miguel Hernández Lobato Universidad Autónoma de Madrid, Computer Science Department June 28, 2007 1/ 32 Outline 1 Introduction 2 Competitive and collaborative

More information

Multivariate Statistics

Multivariate Statistics Multivariate Statistics Chapter 2: Multivariate distributions and inference Pedro Galeano Departamento de Estadística Universidad Carlos III de Madrid pedro.galeano@uc3m.es Course 2016/2017 Master in Mathematical

More information

Ernesto Mordecki 1. Lecture III. PASI - Guanajuato - June 2010

Ernesto Mordecki 1. Lecture III. PASI - Guanajuato - June 2010 Optimal stopping for Hunt and Lévy processes Ernesto Mordecki 1 Lecture III. PASI - Guanajuato - June 2010 1Joint work with Paavo Salminen (Åbo, Finland) 1 Plan of the talk 1. Motivation: from Finance

More information

Wealth, Information Acquisition and Portfolio Choice: A Correction

Wealth, Information Acquisition and Portfolio Choice: A Correction Wealth, Information Acquisition and Portfolio Choice: A Correction Joel Peress INSEAD There is an error in our 2004 paper Wealth, Information Acquisition and Portfolio Choice. This note shows how to correct

More information

Nonparametric Bayesian Methods (Gaussian Processes)

Nonparametric Bayesian Methods (Gaussian Processes) [70240413 Statistical Machine Learning, Spring, 2015] Nonparametric Bayesian Methods (Gaussian Processes) Jun Zhu dcszj@mail.tsinghua.edu.cn http://bigml.cs.tsinghua.edu.cn/~jun State Key Lab of Intelligent

More information

Generalized Autoregressive Score Models

Generalized Autoregressive Score Models Generalized Autoregressive Score Models by: Drew Creal, Siem Jan Koopman, André Lucas To capture the dynamic behavior of univariate and multivariate time series processes, we can allow parameters to be

More information

Robert Collins CSE586, PSU Intro to Sampling Methods

Robert Collins CSE586, PSU Intro to Sampling Methods Robert Collins Intro to Sampling Methods CSE586 Computer Vision II Penn State Univ Robert Collins A Brief Overview of Sampling Monte Carlo Integration Sampling and Expected Values Inverse Transform Sampling

More information

Alastair Hall ECG 752: Econometrics Spring 2005

Alastair Hall ECG 752: Econometrics Spring 2005 Alastair Hall ECG 752: Econometrics Spring 2005 SAS Handout # 6 Estimation of ARCH models In this handout we consider the estimation of ARCH models for the the US dollar trade weighted exchange index.

More information

Clustering K-means. Clustering images. Machine Learning CSE546 Carlos Guestrin University of Washington. November 4, 2014.

Clustering K-means. Clustering images. Machine Learning CSE546 Carlos Guestrin University of Washington. November 4, 2014. Clustering K-means Machine Learning CSE546 Carlos Guestrin University of Washington November 4, 2014 1 Clustering images Set of Images [Goldberger et al.] 2 1 K-means Randomly initialize k centers µ (0)

More information

Markov chain Monte Carlo

Markov chain Monte Carlo Markov chain Monte Carlo Feng Li feng.li@cufe.edu.cn School of Statistics and Mathematics Central University of Finance and Economics Revised on April 24, 2017 Today we are going to learn... 1 Markov Chains

More information

Can we do statistical inference in a non-asymptotic way? 1

Can we do statistical inference in a non-asymptotic way? 1 Can we do statistical inference in a non-asymptotic way? 1 Guang Cheng 2 Statistics@Purdue www.science.purdue.edu/bigdata/ ONR Review Meeting@Duke Oct 11, 2017 1 Acknowledge NSF, ONR and Simons Foundation.

More information

A Correction. Joel Peress INSEAD. Abstract

A Correction. Joel Peress INSEAD. Abstract Wealth, Information Acquisition and ortfolio Choice A Correction Joel eress INSEAD Abstract There is an error in my 2004 paper Wealth, Information Acquisition and ortfolio Choice. This note shows how to

More information

Statistics: Learning models from data

Statistics: Learning models from data DS-GA 1002 Lecture notes 5 October 19, 2015 Statistics: Learning models from data Learning models from data that are assumed to be generated probabilistically from a certain unknown distribution is a crucial

More information

Bickel Rosenblatt test

Bickel Rosenblatt test University of Latvia 28.05.2011. A classical Let X 1,..., X n be i.i.d. random variables with a continuous probability density function f. Consider a simple hypothesis H 0 : f = f 0 with a significance

More information

Supplement to Quantile-Based Nonparametric Inference for First-Price Auctions

Supplement to Quantile-Based Nonparametric Inference for First-Price Auctions Supplement to Quantile-Based Nonparametric Inference for First-Price Auctions Vadim Marmer University of British Columbia Artyom Shneyerov CIRANO, CIREQ, and Concordia University August 30, 2010 Abstract

More information

April 20th, Advanced Topics in Machine Learning California Institute of Technology. Markov Chain Monte Carlo for Machine Learning

April 20th, Advanced Topics in Machine Learning California Institute of Technology. Markov Chain Monte Carlo for Machine Learning for for Advanced Topics in California Institute of Technology April 20th, 2017 1 / 50 Table of Contents for 1 2 3 4 2 / 50 History of methods for Enrico Fermi used to calculate incredibly accurate predictions

More information

A New Independence Test for VaR violations

A New Independence Test for VaR violations A New Independence Test for VaR violations P. Araújo Santos and M.I. Fraga Alves Abstract Interval forecasts evaluation can be reduced to examining the unconditional coverage and independence properties

More information

Piotr Majer Risk Patterns and Correlated Brain Activities

Piotr Majer Risk Patterns and Correlated Brain Activities Alena My²i ková Piotr Majer Song Song Alena Myšičková Peter N. C. Mohr Peter N. C. Mohr Wolfgang K. Härdle Song Song Hauke R. Heekeren Wolfgang K. Härdle Hauke R. Heekeren C.A.S.E. Centre C.A.S.E. for

More information

Computer Vision Group Prof. Daniel Cremers. 11. Sampling Methods: Markov Chain Monte Carlo

Computer Vision Group Prof. Daniel Cremers. 11. Sampling Methods: Markov Chain Monte Carlo Group Prof. Daniel Cremers 11. Sampling Methods: Markov Chain Monte Carlo Markov Chain Monte Carlo In high-dimensional spaces, rejection sampling and importance sampling are very inefficient An alternative

More information

Question 1 carries a weight of 25%; question 2 carries 25%; question 3 carries 20%; and question 4 carries 30%.

Question 1 carries a weight of 25%; question 2 carries 25%; question 3 carries 20%; and question 4 carries 30%. UNIVERSITY OF EAST ANGLIA School of Economics Main Series PGT Examination 2017-18 FINANCIAL ECONOMETRIC THEORY ECO-7024A Time allowed: 2 HOURS Answer ALL FOUR questions. Question 1 carries a weight of

More information

A comparison of four different block bootstrap methods

A comparison of four different block bootstrap methods Croatian Operational Research Review 189 CRORR 5(014), 189 0 A comparison of four different block bootstrap methods Boris Radovanov 1, and Aleksandra Marcikić 1 1 Faculty of Economics Subotica, University

More information

COMS 4721: Machine Learning for Data Science Lecture 19, 4/6/2017

COMS 4721: Machine Learning for Data Science Lecture 19, 4/6/2017 COMS 4721: Machine Learning for Data Science Lecture 19, 4/6/2017 Prof. John Paisley Department of Electrical Engineering & Data Science Institute Columbia University PRINCIPAL COMPONENT ANALYSIS DIMENSIONALITY

More information

Estimating the Pure Characteristics Demand Model: A Computational Note

Estimating the Pure Characteristics Demand Model: A Computational Note Estimating the Pure Characteristics Demand Model: A Computational Note Minjae Song School of Economics, Georgia Institute of Technology April, 2006 Abstract This paper provides details of the computational

More information

LECTURE 10: NEYMAN-PEARSON LEMMA AND ASYMPTOTIC TESTING. The last equality is provided so this can look like a more familiar parametric test.

LECTURE 10: NEYMAN-PEARSON LEMMA AND ASYMPTOTIC TESTING. The last equality is provided so this can look like a more familiar parametric test. Economics 52 Econometrics Professor N.M. Kiefer LECTURE 1: NEYMAN-PEARSON LEMMA AND ASYMPTOTIC TESTING NEYMAN-PEARSON LEMMA: Lesson: Good tests are based on the likelihood ratio. The proof is easy in the

More information

Stat 366 A1 (Fall 2006) Midterm Solutions (October 23) page 1

Stat 366 A1 (Fall 2006) Midterm Solutions (October 23) page 1 Stat 366 A1 Fall 6) Midterm Solutions October 3) page 1 1. The opening prices per share Y 1 and Y measured in dollars) of two similar stocks are independent random variables, each with a density function

More information

Multivariate statistical methods and data mining in particle physics

Multivariate statistical methods and data mining in particle physics Multivariate statistical methods and data mining in particle physics RHUL Physics www.pp.rhul.ac.uk/~cowan Academic Training Lectures CERN 16 19 June, 2008 1 Outline Statement of the problem Some general

More information

Multiscale local change point detection with with applications to Value-at-Risk

Multiscale local change point detection with with applications to Value-at-Risk Multiscale local change point detection with with applications to Value-at-Risk Spokoiny, Vladimir Weierstrass-Institute, Mohrenstr. 39, 10117 Berlin, Germany spokoiny@wias-berlin.de Chen, Ying Weierstrass-Institute,

More information

Independent and conditionally independent counterfactual distributions

Independent and conditionally independent counterfactual distributions Independent and conditionally independent counterfactual distributions Marcin Wolski European Investment Bank M.Wolski@eib.org Society for Nonlinear Dynamics and Econometrics Tokyo March 19, 2018 Views

More information

Variance Reduction Techniques for Monte Carlo Simulations with Stochastic Volatility Models

Variance Reduction Techniques for Monte Carlo Simulations with Stochastic Volatility Models Variance Reduction Techniques for Monte Carlo Simulations with Stochastic Volatility Models Jean-Pierre Fouque North Carolina State University SAMSI November 3, 5 1 References: Variance Reduction for Monte

More information

The Particle Filter. PD Dr. Rudolph Triebel Computer Vision Group. Machine Learning for Computer Vision

The Particle Filter. PD Dr. Rudolph Triebel Computer Vision Group. Machine Learning for Computer Vision The Particle Filter Non-parametric implementation of Bayes filter Represents the belief (posterior) random state samples. by a set of This representation is approximate. Can represent distributions that

More information

Arma-Arch Modeling Of The Returns Of First Bank Of Nigeria

Arma-Arch Modeling Of The Returns Of First Bank Of Nigeria Arma-Arch Modeling Of The Returns Of First Bank Of Nigeria Emmanuel Alphonsus Akpan Imoh Udo Moffat Department of Mathematics and Statistics University of Uyo, Nigeria Ntiedo Bassey Ekpo Department of

More information

Discretization of SDEs: Euler Methods and Beyond

Discretization of SDEs: Euler Methods and Beyond Discretization of SDEs: Euler Methods and Beyond 09-26-2006 / PRisMa 2006 Workshop Outline Introduction 1 Introduction Motivation Stochastic Differential Equations 2 The Time Discretization of SDEs Monte-Carlo

More information

Multiscale and multilevel technique for consistent segmentation of nonstationary time series

Multiscale and multilevel technique for consistent segmentation of nonstationary time series Multiscale and multilevel technique for consistent segmentation of nonstationary time series Haeran Cho Piotr Fryzlewicz University of Bristol London School of Economics INSPIRE 2009 Imperial College London

More information