Copula goodnessoffit testing. An overview and power comparison


 Randolf Foster
 1 years ago
 Views:
Transcription
1 : An overview and power comparison DANIEL BERG DnB NOR Asset Management 22nd Nordic Conference on Mathematical Statistics. Vilnius, Lithuania June 2008
2 Outline Preliminaries Proposed approaches Monte Carlo simulation results and recommendations
3 Motivation Figure: Two simulated data sets  both with standard normal margins and correlation coefficient 0.7.
4 Motivation Figure: Nonzero precipitation values in two Norwegian cities and its copula.
5 Definition & Theorem Definition (Copula) A ddimensional copula is a multivariate distribution function C with standard uniform marginal distributions. Theorem (Sklar, 1959) Let H be a joint distribution function with margins F 1,..., F d. Then there exists a copula C : [0, 1] d [0, 1] such that H(x 1,..., x d ) = C(F 1 (x 1 ),..., F d (x d )).
6 Useful results A general ddimensional density h can be expressed, for some copula density c, as h(x 1,..., x d ) = c{f 1 (x 1 ),..., F d (x d )}f 1 (x 1 ) f d (x d ). Nonparametric estimate for F i (x i ) commonly used to transform original margins into standard uniform: u ji = F i (x ji ) = R ji n + 1, where R ji is the rank of x ji amongst x 1i,..., x ni. u ji commonly referred to as pseudoobservations and models based on nonparametric margins and parametric copulas are referred to as semiparametric copulas
7 Preliminaries Proposed approaches H 0 : C C = {C θ ; θ Θ} vs. H 1 : C / C = {C θ ; θ Θ} Univariate AndersonDarling or QQplot, Multivariate fewer alternatives Pseudoobservations no longer independent. In addition, limiting distribution of many copula GoF test depends on null hypothesis copula and parameter value pvalue estimation via parametric bootstrap procedures Focus in literature almost exclusively bivariate NOT model selection! Several techniques proposed: binning, multivariate smoothing, dimension reduction
8 Preliminaries Proposed approaches Preliminaries Rosenblatt s transform: Dependent variables independent U[0, 1] variables, given multivariate distribution v = R(z) = (R 1 (z 1 ),..., R d (z d )): v 1 = R 1 (z 1 ) = F 1 (z 1 ) = z 1, v 2 = R 2 (z 2 ) = F 2 1 (z 2 z 1 ),. v d = R d (z d ) = F d 1...d (z d z 1,..., z d ). Inverse of simulation (conditional inversion) GoF: v = R(z) test v for independence d! different permutation orders
9 Preliminaries Proposed approaches Proposed approaches: A 1 (1/9) v = R(z) W 1j = d i=1 Γ{v ji; α}, j = 1,..., n Special case (a): d i=1 Φ 1 (v ji ) 2 Special case (b): d i=1 v ji 0.5 S 1 (t) = P{F 1 (W 1 ) t}, t [0, 1] CvM statistic: T 1 = n 1 0 } 2 {Ŝ1 (t) S 1 (t) ds1 (t) References: Breymann et al. (2003); Malevergne and Sornette (2003); Berg and Bakken (2005)
10 Preliminaries Proposed approaches Proposed approaches: A 2 (2/9) Empirical copula: Ĉ(u) = 1 n + 1 CvM statistic: T 2 = n [0,1] d n I {Z j1 u 1,..., Z jd u d } j=1 {Ĉ(z) Cbθ (z) } 2 d Ĉ(z) References: Fermanian (2005); Genest and Rémillard (2008); Genest et al. (2008)
11 Preliminaries Proposed approaches Proposed approaches: A 3 (3/9) Approach A 2 on v = R(z) CvM statistic: T 3 = n [0,1] d References: Genest et al. (2008) } 2 {Ĉ(v) C (v) d Ĉ(v)
12 Preliminaries Proposed approaches Proposed approaches: A 4 (4/9) Cdf of empirical copula (Kendall s dependence function): CvM statistic: T 4 = n S 4 (t) = P{C(z) t} 1 0 {Ŝ4 (t) S 4, bθ (t) } 2 ds4, bθ (t) References: Genest and Rivest (1993); Wang and Wells (2000); Savu and Trede (2004); Genest et al. (2006)
13 Preliminaries Proposed approaches Proposed approaches: A 5 (5/9) Spearman s dependence function: CvM statistic: T 5 = n S 5 (t) = P{C (z) t} 1 References: Quessy et al. (2007) 0 {Ŝ5 (t) S 5, bθ (t) } 2 ds5, bθ (t)
14 Preliminaries Proposed approaches Proposed approaches: A 6 (6/9) Shih s test for bivariate gamma frailty model (Clayton): T Shih = n { θτ θ } W Extension to arbitrary dimension: T 6 = d 1 d { θτ,ij θ W,ij } 2 i=1 j=i+1 References: Shih (1998); Berg (2007)
15 Preliminaries Proposed approaches Proposed approaches: A 7 (7/9) Inner product of two vectors = 0 iff from the same family Q(z) = z z bθ κ d z z bθ κ a symmetric kernel, e.g. the gaussian kernel: κ d (z, z bθ ) = exp { z z bθ 2 /(2dh 2 ) } Statistic becomes: T 7 = 1 n n n 2 n i=1 j=1 i=1 j=1 n κ d (z i, z j ) 2 n 2 n κ d (z bθ,i, z bθ,j ) References: Panchenko (2005) n i=1 j=1 n κ d (z i, z bθ,j )
16 Preliminaries Proposed approaches Proposed approaches: A 8 (8/9) Approach A 7 on v = R(z) Statistic: T 8 = 1 n n n 2 κ d (v i, v j ) 2 n n 2 n i=1 j=1 i=1 j=1 n κ d (v bθ,i, v bθ,j ) n n κ d (v i, v bθ,j ) i=1 j=1 References: Berg (2007)
17 Preliminaries Proposed approaches Proposed approaches: A 9 (9/9) Each approach may detect deviations from H 0 differently Average approaches: T (a) 9 = 1 9 T (b) 9 = 1 3 References: Berg (2007) { T (a) (b) 1 + T 1 + { T2 + T 3 + T 4 } } 8 T k k=2
18 Test procedure Experimental setup Power comparison Monte Carlso simulations Test procedure 1) x n samples from the ddimensional H 1 copula with θ(τ). 2) z pseudoobservations (normalized ranks) 3) ˆθ estimated parameter of the H 0 copula 4) T i test statistic i computed under the H 0 copula using ˆθ. 5) Repeat steps 14 M times with H 1 = H 0 and θ = ˆθ T 0 i,m 6) ˆp = 1 M M m=1 1( T 0 i,m > T i ) 7) ˆp < 5% reject H 0
19 Test procedure Experimental setup Power comparison Monte Carlso simulations Experimental setup H 0 copula (5 choices: Gaussian, Student, Clayton, Gumbel, Frank), H 1 copula (5 choices: Gaussian, Student (ν = 6), Clayton, Gumbel, Frank), Kendall s tau (2 choices: τ = {0.2, 0.4}), Dimension (3 choices: d = {2, 4, 8}), Sample size (2 choices: n = {100, 500}) Student only considered as null in bivariate case. For each of these 240 cases, 10, 000 repetitions size/power
20 Test procedure Experimental setup Power comparison Monte Carlso simulations Testing the Gaussian copula Power difference (%) A 1 (a) A 1 (b) A 2 A 3 A 4 A 5 A 7 A 8 A 9 (a) A 9 (b)
21 Test procedure Experimental setup Power comparison Monte Carlso simulations Testing the Student copula Power difference (%) A 1 (a) A 1 (b) A 2 A 3 A 4 A 5 A 7 A 8 A 9 (a) A 9 (b)
22 Test procedure Experimental setup Power comparison Monte Carlso simulations Testing the Clayton copula Power difference (%) A 1 (a) A 1 (b) A 2 A 3 A 4 A 5 A 6 A 7 A 8 A 9 (a) A 9 (b)
23 Test procedure Experimental setup Power comparison Monte Carlso simulations Testing the Gumbel copula Power difference (%) A 1 (a) A 1 (b) A 2 A 3 A 4 A 5 A 7 A 8 A 9 (a) A 9 (b)
24 Test procedure Experimental setup Power comparison Monte Carlso simulations Testing the Frank copula Power difference (%) A 1 (a) A 1 (b) A 2 A 3 A 4 A 5 A 7 A 8 A 9 (a) A 9 (b)
25 and recommendations Nominal levels all match prescribed size of 5% Power generally increases with dimension, sample size and dependence Clayton > Gumbel > Frank > Gaussian > Student (>: easier to test) No universally most powerful approach, but A 2, A 4 and A (b) 9 perform very well in most cases A (b) 9 is recommended in general, with special case exceptions: For testing the Gaussian copula, if trying to detect heavy tails for d > 2 and large n then A 1 very powerful For testing the Clayton copula the generalized Shih s test is most powerful Permutational variation of little concern for approaches based on Rosenblatt s transform (see Berg (2007))
26 References Berg, D. (2007). : an overview and power comparison. Technical report, University of Oslo. Statistical research report no. 5, ISSN Berg, D. and H. Bakken (2005). A goodnessoffit test for copulae based on the probability integral transform. Technical report, University of Oslo. Statistical research report no. 10, ISSN Breymann, W., A. Dias, and P. Embrechts (2003). Dependence structures for multivariate highfrequency data in finance. Quantitative Finance 1, Fermanian, J. (2005). Goodness of fit tests for copulas. Journal of Multivariate Analysis 95, Genest, C., J.F. Quessy, and B. Rémillard (2006). Goodnessoffit procedures for copula models based on the probability integral transform. Scandinavian Journal of Statistics 33, Genest, C. and B. Rémillard (2008). Validity of the parametric bootstrap for goodnessoffit testing in semiparametric models. Ann. Henri Poincaré 44. In press. Genest, C., B. Rémillard, and D. Beaudoin (2008). Omnibus goodnessoffit tests for copulas: A review and a power study. Insurance: Mathematics and Economics 42. In press. Genest, C. and L.P. Rivest (1993). Statistical inference procedures for bivariate archimedean copulas. Journal of the American Statistical Association, Malevergne, Y. and D. Sornette (2003). Testing the gaussian copula hypothesis for financial assets dependence. Quantitative Finance 3, Panchenko, V. (2005). Goodnessoffit test for copulas. Physica A 355(1), Quessy, J.F., M. Mesfioui, and M.H. Toupin (2007). A goodnessoffit test based on Spearmans dependence function. Working paper, Université du Québec à TroisRivières. Savu, C. and M. Trede (2004). Goodnessoffit tests for parametric families of archimedean copulas. CAWM discussion paper, No. 6. Shih, J. H. (1998). A goodnessoffit test for association in a bivariate survival model. Biometrika 85, Wang, W. and M. T. Wells (2000). Model selection and semiparametric inference for bivariate failuretime data. Journal of the American Statistical Association 95,
Copula goodnessoft testing. An overview and power comparison DANIEL BERG. University of Oslo & Norwegian Computing Center
: An overview and power comparison DANIEL BERG University of Oslo & Norwegian Computing Center Conference on copulae and multivariate probability distributions in nance theory, applications, opportunities
More informationCopula goodnessoffit testing: an overview and power comparison
Dept. of Math. University of Oslo Statistical Research Report No. 5 ISSN 0806 3842 October 2007 Copula goodnessoffit testing: an overview and power comparison Daniel Berg University of Oslo and Norwegian
More informationA Goodnessoffit Test for Copulae Based on the Probability Integral Transform
Dept. of Math. University of Oslo Statistical Research Report No. 10 ISSN 0806 3842 December 2005 A Goodnessoffit Test for Copulae Based on the Probability Integral Transform Daniel Berg Department of
More informationCOpula have proved to be a very useful tool in the
Comparison of Two Methods to Check Copula Fitting Yan Fang, Lisa Madsen, and Ling Liu Abstract The novelty of this paper is how we quickly and accurately choose the true copula if we know the true copula
More informationCopula Parameter Estimation by Maximum Likelihood and Minimum Distance Estimators A Simulation Study
Gregor Weiß Copula Parameter Estimation by Maximum Likelihood and Minimum Distance Estimators A Simulation Study Presentation at the workshop Finance and Insurance FSU Jena, March 1620, 2009. Gregor
More informationActuarial and Financial Mathematics Conference Interplay between finance and insurance
KONINKLIJKE VLAAMSE ACADEMIE VAN BELGIE VOOR WETENSCHAPPEN EN KUNSTEN Actuarial and Financial Mathematics Conference Interplay between finance and insurance CONTENTS Invited talk Optimal investment under
More informationModelling the dependence structure of financial assets: A survey of four copulas
Modelling the dependence structure of financial assets: A survey of four copulas Gaussian copula Clayton copula NORDIC 0.05 0.0 0.05 0.10 NORDIC NORWAY NORWAY Student s tcopula Gumbel copula NORDIC NORDIC
More informationPaircopula constructions of multiple dependence
Paircopula constructions of multiple dependence Kjersti Aas The Norwegian Computing Center, Oslo, Norway Claudia Czado Technische Universität, München, Germany Arnoldo Frigessi Centre for Statistics for
More informationTail Dependence among Agricultural Insurance Indices: The Case of Iowa CountyLevel Rainfalls
Tail Dependence among Agricultural Insurance Indices: The Case of Iowa CountyLevel Rainfalls Pu Liu Research Assistant, Department of Agricultural, Environmental and Development Economics, The Ohio State
More informationA GoodnessofFit Test for Multivariate Multiparameter Copulas Based on Multiplier Central Limit Theorems
A GoodnessofFit Test for Multivariate Multiparameter Copulas Based on Multiplier Central Limit Theorems Ivan Kojadinovic Department of Statistics The University of Auckland, Private Bag 9019 Auckland
More informationPaircopula constructions of multiple dependence
Paircopula constructions of multiple dependence Kjersti Aas The Norwegian Computing Center, Oslo, Norway Claudia Czado Technische Universität, München, Germany Arnoldo Frigessi University of Oslo and
More informationAmath 546/Econ 589 Copulas
Amath 546/Econ 589 Copulas Eric Zivot Updated: May 15, 2012 Reading FRF chapter 1 QRM chapter 4, sections 5 and 6; chapter 5 FMUND chapter 6 SDAFE chapter 8 Introduction Capturing comovement between financial
More informationUncertainty quantification for the familywise error rate in multivariate copula models
Uncertainty quantification for the familywise error rate in multivariate copula models Thorsten Dickhaus (joint work with Taras Bodnar, Jakob Gierl and Jens Stange) University of Bremen Institute for
More informationCopulas: An Introduction I  Fundamentals
Copulas: An Introduction I  Fundamentals Johan Segers Université catholique de Louvain (BE) Institut de statistique, biostatistique et sciences actuarielles Columbia University, New York City 9 11 Oct
More informationModels for construction of multivariate dependence: A comparison study
Models for construction of multivariate dependence: A comparison study Daniel Berg University of Oslo & The Norwegian Computing Center. Email: daniel@danielberg.no Kjersti Aas The Norwegian Computing
More informationA Comparison of Correlation Coefficients via a ThreeStep Bootstrap Approach
ISSN: 19169795 Journal of Mathematics Research A Comparison of Correlation Coefficients via a ThreeStep Bootstrap Approach Tahani A. Maturi (Corresponding author) Department of Mathematical Sciences,
More informationPricing of a worst of option using a Copula method M AXIME MALGRAT
Pricing of a worst of option using a Copula method M AXIME MALGRAT Master of Science Thesis Stockholm, Sweden 2013 Pricing of a worst of option using a Copula method MAXIME MALGRAT Degree Project in Mathematical
More informationMODELLING INCURRED BUT NOT REPORTED CLAIM RESERVE USING COPULAS
MODELLING INCURRED BUT NOT REPORTED CLAIM RESERVE USING COPULAS Gaida Pettere Professor, Dr. Math. Banking Institution of Higher Education, Riga, Latvia In practice of an insurance company claims occur
More informationNonparametric Statistics
Nonparametric Statistics References Some good references for the topics in this course are 1. Higgins, James (2004), Introduction to Nonparametric Statistics 2. Hollander and Wolfe, (1999), Nonparametric
More informationLecture 4: Bivariate and Multivariate Failure Times
Lecture 4: Bivariate and Multivariate Failure Times In many survival studies, the failure times may be clustered, matched or repeatedly measured, and failure times are likely to be correlated. The choice
More informationCopulas A copula is the joint distribution of random variables U 1, U 2,..., U p, each of which is marginally uniformly distributed
Copulas A copula is the joint distribution of random variables U 1, U 2,..., U p, each of which is marginally uniformly distributed as U(0, 1). The term copula is also used for the joint cumulative distribution
More informationESTIMATING IBNR CLAIM RESERVES FOR GENERAL INSURANCE USING ARCHIMEDEAN COPULAS
ESTIMATING IBNR CLAIM RESERVES FOR GENERAL INSURANCE USING ARCHIMEDEAN COPULAS Caroline Ratemo and Patrick Weke School of Mathematics, University of Nairobi, Kenya ABSTRACT There has always been a slight
More informationON MODELING INSURANCE CLAIMS
ON MODELING INSURANCE CLAIMS USING COPULAS FILIP ERNTELL Master s thesis 213:E55 Faculty of Science Centre for Mathematical Sciences Mathematical Statistics CENTRUM SCIENTIARUM MATHEMATICARUM ON MODELING
More informationPaircopula constructions: even more flexible than copulas
Paircopula constructions: even more flexible than copulas Workshop on Copulas and Extremes Grenoble, France, November 19th, 2013 Kjersti Aas Norwegian Computing Center Joint work with: Claudia Czado,
More informationMeasuring Portfolio Value at Risk
Measuring Portfolio Value at Risk Chao Xu 1, Huigeng Chen 2 Supervisor: Birger Nilsson Department of Economics School of Economics and Management, Lund University May 2012 1 saintlyjinn@hotmail.com 2 chenhuigeng@gmail.com
More informationRecognizing and visualizing copulas: an approach using local Gaussian approximation
Recognizing and visualizing copulas: an approach using local Gaussian approximation Geir Drage Berentsen, Bård Støve, Dag Tjøstheim and Tommy Nordbø 30th April 2013 Abstract Copulas are much used to model
More informationNonparametric Tests for Randomness
ECE 461 PROJECT REPORT, MAY 2003 1 Nonparametric Tests for Randomness Ying Wang ECE 461 PROJECT REPORT, MAY 2003 2 Abstract To decide whether a given sequence is truely random, or independent and identically
More informationPackage CoImp. February 19, 2015
Title Copula based imputation method Date 20140301 Version 0.23 Package CoImp February 19, 2015 Author Francesca Marta Lilja Di Lascio, Simone Giannerini Depends R (>= 2.15.2), methods, copula Imports
More informationBivariate Archimedean copulas: an application to two stock market indices
Vrije Universiteit Amsterdam BMI Paper Bivariate Archimedean copulas: an application to two stock market indices M. Mahfoud  1517333 Supervisor  Dr. Michael Massmann Keywords: Risk management; econometric
More informationTailDependence an Essential Factor for Correctly Measuring the Benefits of Diversification
TailDependence an Essential Factor for Correctly Measuring the Benefits of Diversification Presented by Work done with Roland Bürgi and Roger Iles New Views on Extreme Events: Coupled Networks, Dragon
More informationA copulabased model for risk aggregation
Actuarial Research Conference 2014 & Christian Genest Department of Mathematics and Statistics, McGill University July 14, 2014 Objective Introduction To model adequately dependent insurance portfolios
More informationPortfolio Distribution Modelling and Computation. Harry Zheng Department of Mathematics Imperial College h.zheng@imperial.ac.uk
Portfolio Distribution Modelling and Computation Harry Zheng Department of Mathematics Imperial College h.zheng@imperial.ac.uk Workshop on Fast Financial Algorithms Tanaka Business School Imperial College
More informationA GENERALIZED DEFINITION OF THE POLYCHORIC CORRELATION COEFFICIENT
A GENERALIZED DEFINITION OF THE POLYCHORIC CORRELATION COEFFICIENT JOAKIM EKSTRÖM Abstract. The polychoric correlation coefficient is a measure of association for ordinal variables which rests upon an
More informationModeling Operational Risk: Estimation and Effects of Dependencies
Modeling Operational Risk: Estimation and Effects of Dependencies Stefan Mittnik Sandra Paterlini Tina Yener Financial Mathematics Seminar March 4, 2011 Outline Outline of the Talk 1 Motivation Operational
More informationRisk Aggregation, Dependence Structure and Diversification Benefits
Risk Aggregation, Dependence Structure and Diversification Benefits Presented by Michel M. Dacorogna Work done with Roland Bürgi and Roger Iles Financial Mathematics and Applied Probability Seminars, King
More informationCopula Goodnessoffit Tests: A Comparative Study
Copula oodnessoffit Tests: A Comparative Study Daniel erg The Norwegian Computing Center and University of Oslo. Email: daniel@danielberg.no Henrik akken The Norwegian Computing Center and The Norwegian
More informationPenalized Splines  A statistical Idea with numerous Applications...
Penalized Splines  A statistical Idea with numerous Applications... Göran Kauermann LudwigMaximiliansUniversity Munich Graz 7. September 2011 1 Penalized Splines  A statistical Idea with numerous Applications...
More informationGaussian Copula Vs. Loans Loss Assessment: A Simplified And EasyToUse Model Viviane Y. Naïmy, Ph.D., Notre Dame University, Louaize, Lebanon
Gaussian Copula Vs. Loans Loss Assessment: A Simplified And EasyToUse Model Viviane Y. Naïmy, Ph.D., Notre Dame University, Louaize, Lebanon ABSTRACT The copula theory is a fundamental instrument used
More informationIntroduction to Hypothesis Testing. Point estimation and confidence intervals are useful statistical inference procedures.
Introduction to Hypothesis Testing Point estimation and confidence intervals are useful statistical inference procedures. Another type of inference is used frequently used concerns tests of hypotheses.
More informationEstimation of the Dependence Parameter in Bivariate Archimedean Copula Models Under Misspecification
Estimation of the Dependence Parameter in Bivariate Archimedean Copula Models Under Misspecification Master s Thesis submitted to Prof. Dr. Ostap Okhrin HumboldtUniversität zu Berlin School of Business
More informationWorking Paper A simple graphical method to explore taildependence
econstor www.econstor.eu Der OpenAccessPublikationsserver der ZBW LeibnizInformationszentrum Wirtschaft The Open Access Publication Server of the ZBW Leibniz Information Centre for Economics Abberger,
More informationMultivariate Option Pricing Using Copulae
Multivariate Option Pricing Using Copulae Carole Bernard and Claudia Czado November 23, 2010 Abstract: The complexity of financial products significantly increased in the past ten years. In this paper
More informationCopula Simulation in Portfolio Allocation Decisions
Copula Simulation in Portfolio Allocation Decisions Gyöngyi Bugár Gyöngyi Bugár and Máté Uzsoki University of Pécs Faculty of Business and Economics This presentation has been prepared for the Actuaries
More informationModelling the Dependence Structure of MUR/USD and MUR/INR Exchange Rates using Copula
International Journal of Economics and Financial Issues Vol. 2, No. 1, 2012, pp.2732 ISSN: 21464138 www.econjournals.com Modelling the Dependence Structure of MUR/USD and MUR/INR Exchange Rates using
More informationPackage depend.truncation
Type Package Package depend.truncation May 28, 2015 Title Statistical Inference for Parametric and Semiparametric Models Based on Dependently Truncated Data Version 2.4 Date 20150528 Author Takeshi Emura
More informationStudy Guide for the Final Exam
Study Guide for the Final Exam When studying, remember that the computational portion of the exam will only involve new material (covered after the second midterm), that material from Exam 1 will make
More informationForecasting commodity futures using Principal Component Analysis and Copula. Martin Jacobsson
Forecasting commodity futures using Principal Component Analysis and Copula Martin Jacobsson May 20, 2015 Abstract The ever ongoing battle to beat the market is in this thesis fought with the help of mathematics
More informationACTEX ERM Study Manual Spring 2015 Edition. Please replace pages B45 through B54 with the following pages. ACTEX 2015 ERM Study Manual
ACTEX ERM Study Manual Spring 205 Edition Please replace pages B45 through B54 with the following pages. ACTEX 205 ERM Study Manual ERM032 B45 Basel Committee Technical Underpinnings of Aggregation
More informationStatistics with Excel Examples
Statistics with Ecel Eamples Questions What is a probability density function (pdf)? What is a cumulative density function (cdf)? What is an inverse cdf? Eamples of distributions: Uniform, Normal, Beta,
More informationCopulas in Macroeconomics
Dowd, Journal of International and global Economic Studies, 1(1), June 2008, 126 1 Copulas in Macroeconomics Kevin Dowd * Centre for Risk and Insurance Studies Nottingham University Business School Abstract
More informationAn Internal Model for Operational Risk Computation
An Internal Model for Operational Risk Computation Seminarios de Matemática Financiera Instituto MEFFRiskLab, Madrid http://www.risklabmadrid.uam.es/ Nicolas Baud, Antoine Frachot & Thierry Roncalli
More informationAPPLYING COPULA FUNCTION TO RISK MANAGEMENT. Claudio Romano *
APPLYING COPULA FUNCTION TO RISK MANAGEMENT Claudio Romano * Abstract This paper is part of the author s Ph. D. Thesis Extreme Value Theory and coherent risk measures: applications to risk management.
More informationOlgierd Hryniewicz Janusz Karpiński. 1. Introduction
Article citation info: Hryniewicz O, Karpiński J. Prediction of reliability the pitfalls of using Pearson s correlation. Eksploatacja i Niezawodnosc Maintenance and Reliability 2014; 16 (3): 472 483. Olgierd
More informationPREDICTING MULTIVARIATE INSURANCE LOSS PAYMENTS UNDER THE BAYESIAN COPULA FRAMEWORK
PREDICTING MULTIVARIATE INSURANCE LOSS PAYMENTS UNDER THE BAYESIAN COPULA FRAMEWORK YANWEI ZHANG CNA INSURANCE COMPANY VANJA DUKIC APPLIED MATH UNIVERSITY OF COLORADOBOULDER Abstract. The literature of
More informationThe Modified KolmogorovSmirnov OneSample Test Statistic
Thailand Statistician July 00; 8() : 4355 http://statassoc.or.th Contributed paper The Modified KolmogorovSmirnov OneSample Test Statistic Jantra Sukkasem epartment of Mathematics, Faculty of Science,
More informationAn analysis of the dependence between crude oil price and ethanol price using bivariate extreme value copulas
The Empirical Econometrics and Quantitative Economics Letters ISSN 2286 7147 EEQEL all rights reserved Volume 3, Number 3 (September 2014), pp. 1323. An analysis of the dependence between crude oil price
More informationCopula model estimation and test of inventory portfolio pledge rate
International Journal of Business and Economics Research 2014; 3(4): 150154 Published online August 10, 2014 (http://www.sciencepublishinggroup.com/j/ijber) doi: 10.11648/j.ijber.20140304.12 ISS: 23287543
More informationAnalyzing Quantitative Data
Analyzing Quantitative Data From Description to Explanation Norman Blaikie UHOCHSCHULE " LIECHTENSTEIN Bibliothek SAGE Publications London Thousand Oaks» New Delhi Detailed Chapter Contents List of Figures
More informationA Copula Approach to ValueatRisk Estimation for FixedIncome Portfolios
EDHEC RISK AND ASSET MANAGEMENT RESEARCH CENTRE 393400 promenade des Anglais 06202 Nice Cedex 3 Tel.: +33 (0)4 93 18 32 53 Email: research@edhecrisk.com Web: www.edhecrisk.com A Copula Approach to
More informationPower Comparison of Correlation Tests (Simulation)
Chapter 806 Power Comparison of Correlation Tests (Simulation) Introduction This procedure analyzes the power and significance level of tests which may be used to test statistical hypotheses about the
More informationEXTREME VALUE ANALYSIS BASED ON COPULAS AND THEIR DIAGONALS. Maddalena Manzi
EXTREME VALUE ANALYSIS BASED ON COPULAS AND THEIR DIAGONALS Who? From? Maddalena Manzi Ca Foscari University of Venice When? FSTA 2014, Liptovský Ján  Slovak Republic January 30, 2014 Table of contents
More informationStochastic modelling of insurance liabilities
ACTA ET COMMENTATIONES UNIVERSITATIS TARTUENSIS DE MATHEMATICA Volume 13, 2009 Stochastic modelling of insurance liabilities Gaida Pettere Abstract. Our aim is to present a method for estimating incurred
More informationCross generational comparison of stochastic mortality of coupled lives
Cross generational comparison of stochastic mortality of coupled lives Elisa Luciano Jaap Spreeuw Elena Vigna No. 87 December 200 www.carloalberto.org/working_papers 200 by Elisa Luciano, Jaap Spreeuw
More informationCorrelations and Dependencies in Economic Capital Models
Correlations and Dependencies in Economic Capital Models Authors: Richard Shaw MSc(LBS) FIA, HCR Ltd, [richard.shaw@hcruk.com] Grigory Spivak MSc FIA, Towers Perrin, [grigory.spivak@towersperrin.com]
More informationStatistics 641  EXAM II  1999 through 2003
Statistics 641  EXAM II  1999 through 2003 December 1, 1999 I. (40 points ) Place the letter of the best answer in the blank to the left of each question. (1) In testing H 0 : µ 5 vs H 1 : µ > 5, the
More informationTIME DEPENDENT COPULAS
TIME DEPENDENT COPULAS BY JEANDAVID FERMANIAN AND MARTEN WEGKAMP Abstract. For the study of dynamic dependence structures, we introduce the concept of pseudocopulas, extending Patton s (2001a) definition
More informationKendall s Taub Correlation Tests (Simulation)
Chapter 804 Kendall s Taub Correlation Tests (Simulation) Introduction This procedure analyzes the power and significance level of the Kendall s Tau Correlation significance test using Monte Carlo simulation.
More informationSpearman s Rank Correlation Tests (Simulation)
Chapter 803 Spearman s Rank Correlation Tests (Simulation) Introduction This procedure analyzes the power and significance level of Spearman s Rank Correlation significance test using Monte Carlo simulation.
More informationSpatial Statistics Chapter 3 Basics of areal data and areal data modeling
Spatial Statistics Chapter 3 Basics of areal data and areal data modeling Recall areal data also known as lattice data are data Y (s), s D where D is a discrete index set. This usually corresponds to data
More informationGENERATING SIMULATION INPUT WITH APPROXIMATE COPULAS
GENERATING SIMULATION INPUT WITH APPROXIMATE COPULAS Feras Nassaj Johann Christoph Strelen Rheinische FriedrichWilhelmsUniversitaet Bonn Institut fuer Informatik IV Roemerstr. 164, 53117 Bonn, Germany
More informationTails of Copulas Abstract:
Tails of Copulas Abstract: Actuaries who want to model correlated joint distributions have a choice of quite a few copulas, but little basis for choosing one over another. Methods are provided here to
More informationMeasuring Economic Capital: Value at Risk, Expected Tail Loss and Copula Approach
Measuring Economic Capital: Value at Risk, Expected Tail Loss and Copula Approach by Jeungbo Shim, SeungHwan Lee, and Richard MacMinn August 19, 2009 Please address correspondence to: Jeungbo Shim Department
More informationFit to a t Estimation, Application and Limitations of the tcopula Topic 1: Risk Evaluation
Fit to a t Estimation, Application and Limitations of the tcopula Topic : Risk Evaluation Gary G Venter Guy Carpenter Instrat One Madison Avenue, New York NY USA +22323739 Fax: +223904739 gary.g.venter@guycarp.com
More informationSYLLABUS OF BASIC EDUCATION 2017 Construction and Evaluation of Actuarial Models Exam 4
The syllabus for this exam is defined in the form of learning objectives that set forth, usually in broad terms, what the candidate should be able to do in actual practice. Please check the Syllabus Updates
More informationDependence Concepts. by Marta Monika Wawrzyniak. Master Thesis in Risk and Environmental Modelling Written under the direction of Dr Dorota Kurowicka
Dependence Concepts by Marta Monika Wawrzyniak Master Thesis in Risk and Environmental Modelling Written under the direction of Dr Dorota Kurowicka Delft Institute of Applied Mathematics Delft University
More informationInput model uncertainty and reliabilitybased design optimization with associated confidence level
University of Iowa Iowa Research Online Theses and Dissertations Fall 009 Input model uncertainty and reliabilitybased design optimization with associated confidence level Yoojeong Noh University of Iowa
More informationNotes for STA 437/1005 Methods for Multivariate Data
Notes for STA 437/1005 Methods for Multivariate Data Radford M. Neal, 26 November 2010 Random Vectors Notation: Let X be a random vector with p elements, so that X = [X 1,..., X p ], where denotes transpose.
More informationStatistical basics for Biology: p s, alphas, and measurement scales.
334 Volume 25: Mini Workshops Statistical basics for Biology: p s, alphas, and measurement scales. Catherine Teare Ketter School of Marine Programs University of Georgia Athens Georgia 306023636 (706)
More informationCredit Risk Models: An Overview
Credit Risk Models: An Overview Paul Embrechts, Rüdiger Frey, Alexander McNeil ETH Zürich c 2003 (Embrechts, Frey, McNeil) A. Multivariate Models for Portfolio Credit Risk 1. Modelling Dependent Defaults:
More informationMonte Carlo Simulations of the multivariate distributions with different marginals
Monte Carlo Simulations of the multivariate distributions with different marginals Mária Bohdalová Comenius University, Faculty of Management, Department of Information Systems email: maria.bohdalova@fm.uniba.sk
More informationChapter 9: FatTailed Regression Models
Chapter 9: FatTailed Regression Models Peng Shi Northern Illinois University 2013 Ratemaking and Product Management Seminar March 1113, 2013 Peng Shi (Northern Illinois University) FatTailed Regression
More informationitesla Project Innovative Tools for Electrical System Security within Large Areas
itesla Project Innovative Tools for Electrical System Security within Large Areas Samir ISSAD RTE France samir.issad@rtefrance.com PSCC 2014 Panel Session 22/08/2014 Advanced datadriven modeling techniques
More informationStatistics and Probability Letters. Goodnessoffit test for tail copulas modeled by elliptical copulas
Statistics and Probability Letters 79 (2009) 1097 1104 Contents lists available at ScienceDirect Statistics and Probability Letters journal homepage: www.elsevier.com/locate/stapro Goodnessoffit test
More informationTESTING CONDITIONAL INDEPENDENCE FOR CONTINUOUS RANDOM VARIABLES
TESTING CONDITIONAL INDEPENDENCE FOR CONTINUOUS RANDOM VARIABLES Wicher P. Bergsma 3122004 Abstract: A common statistical problem is the testing of independence of two (response) variables conditionally
More informationPricing of pathdependent basket options using a copula approach
Pricing of pathdependent basket options using a copula approach Christ Church University of Oxford A thesis submitted in partial fulfillment of the requirements for the MSc in Mathematical Finance i Abstract
More informationOn Small Sample Properties of Permutation Tests: A Significance Test for Regression Models
On Small Sample Properties of Permutation Tests: A Significance Test for Regression Models Hisashi Tanizaki Graduate School of Economics Kobe University (tanizaki@kobeu.ac.p) ABSTRACT In this paper we
More informationEquivalence Tests for Paired Means (Simulation)
Chapter 495 Equivalence Tests for Paired Means (Simulation) Introduction This procedure allows you to study the power and sample size of tests of equivalence of means of two correlated variables. Schuirmann
More informationComparing the Accuracy of CopulaBased Multivariate Density Forecasts in Selected Regions of Support
Comparing the Accuracy of CopulaBased Multivariate Density Forecasts in Selected Regions of Support Cees Diks CeNDEF, Amsterdam School of Economics University of Amsterdam Oleg Sokolinskiy Econometric
More information1. χ 2 minimization 2. Fits in case of of systematic errors
Data fitting Volker Blobel University of Hamburg March 2005 1. χ 2 minimization 2. Fits in case of of systematic errors Keys during display: enter = next page; = next page; = previous page; home = first
More informationMultivariate Negative Binomial Models for Insurance Claim Counts
Multivariate Negative Binomial Models for Insurance Claim Counts Peng Shi Division of Statistics Northern Illinois University DeKalb, IL 0 Email: pshi@niu.edu Emiliano A. Valdez Department of Mathematics
More informationCORRELATION ANALYSIS: EXACT PERMUTATION PARADIGM. Justice Ighodaro Odiase and Sunday Martins Ogbonmwan
MATEMATIQKI VESNIK 59 (2007), 161 170 UDK 519.24 originalni nauqni rad research paper CORRELATION ANALYSIS: EXACT PERMUTATION PARADIGM Justice Ighodaro Odiase and Sunday Martins Ogbonmwan Abstract. For
More informationGoodness of Fit Tests for the Gumbel Distribution with Type II right Censored data
Revista Colombiana de Estadística Diciembre 2012, volumen 35, no. 3, pp. 409 a 424 Goodness of Fit Tests for the Gumbel Distribution with Type II right Censored data Pruebas de bondad de ajuste para la
More informationOperational Risk Management: Added Value of Advanced Methodologies
Operational Risk Management: Added Value of Advanced Methodologies Paris, September 2013 Bertrand HASSANI Head of Major Risks Management & Scenario Analysis Disclaimer: The opinions, ideas and approaches
More informationInterval estimation for bivariate tcopulas via. Kendall s tau
Interval estimation for bivariate tcopulas via Kendall s tau Liang Peng and Ruodu Wang February 2, 24 Abstract Copula models have been popular in risk management. Due to the properties of asymptotic dependence
More informationNormality Testing in Excel
Normality Testing in Excel By Mark Harmon Copyright 2011 Mark Harmon No part of this publication may be reproduced or distributed without the express permission of the author. mark@excelmasterseries.com
More informationThe Asymmetric tcopula with Individual Degrees of Freedom
The Asymmetric tcopula with Individual Degrees of Freedom dfine GmbH Christ Church University of Oxford A thesis submitted for the degree of MSc in Mathematical Finance Michaelmas 2012 Abstract This
More informationDrought SeverityDurationFrequency Analysis of Hydrological Drought Based on Copula Theory
Hydrology Days 2012 Drought SeverityDurationFrequency Analysis of Hydrological Drought Based on Copula Theory Jaewon, Kwak 1, Yeon Soo, Kim, Jong So, Lee, and Hung Soo, Kim Department of Civil Engineering,
More informationComparing the Accuracy of Copula Based Multivariate Density Forecasts in Selected Regions of Support
TI 2013061/III Tinbergen Institute Discussion Paper Comparing the Accuracy of Copula Based Multivariate Density Forecasts in Selected Regions of Support Cees Diks 1,2 Valentyn Panchenko 3 Oleg Sokolinskiy
More informationTimevarying copulas: a survey
Timevarying copulas: a survey Olga Reznikova Institute of Statistics Université catholique de Louvain joint with Hans Manner Department of Quantitative Economics Maastricht University Young Researchers
More informationDependence structures and limiting results with applications in finance and insurance
Dependence structures and limiting results with applications in finance and insurance Arthur Charpentier, prix scor 2006 Institut des Actuaires, Juin 2007 arthur.charpentier@ensae.fr 1 Présentation Petite
More information