MODELS FOR QUANTIFYING RISK

Similar documents
ACTEX ACADEMIC SERIES

Contents. An Overview of Statistical Applications CHAPTER 1. Contents (ix) Preface... (vii)

Introduction Models for claim numbers and claim sizes

CAS Course 3 - Actuarial Models

Contents Utility theory and insurance The individual risk model Collective risk models

Exam 3L Actuarial Models Life Contingencies and Statistics Segment

Society of Actuaries Exam MLC: Models for Life Contingencies Draft 2012 Learning Objectives Document Version: August 19, 2011

SECOND EDITION. MARY R. HARDY University of Waterloo, Ontario. HOWARD R. WATERS Heriot-Watt University, Edinburgh

Fundamentals of Actuarial Mathematics

2.1 Random variable, density function, enumerative density function and distribution function

Institute of Actuaries of India Subject CT6 Statistical Methods

Subject CS2A Risk Modelling and Survival Analysis Core Principles

Changes to Exams FM/2, M and C/4 for the May 2007 Administration

1. For a special whole life insurance on (x), payable at the moment of death:

Cambridge University Press Risk Modelling in General Insurance: From Principles to Practice Roger J. Gray and Susan M.

UPDATED IAA EDUCATION SYLLABUS

MODELS QUANTIFYING RISK FOR SECOND EDITION ROBIN J. CUNNINGHAM, FSA, PH.D. THOMAS N. HERZOG, ASA, PH.D. RICHARD L. LONDON, FSA

PROBABILITY. Wiley. With Applications and R ROBERT P. DOBROW. Department of Mathematics. Carleton College Northfield, MN

Discrete-time Asset Pricing Models in Applied Stochastic Finance

Syllabus 2019 Contents

A First Course in Probability

Financial Models with Levy Processes and Volatility Clustering

Content Added to the Updated IAA Education Syllabus

Market Risk Analysis Volume I

2017 IAA EDUCATION SYLLABUS

Contents Part I Descriptive Statistics 1 Introduction and Framework Population, Sample, and Observations Variables Quali

Exam M Fall 2005 PRELIMINARY ANSWER KEY

1. For two independent lives now age 30 and 34, you are given:

**BEGINNING OF EXAMINATION** A random sample of five observations from a population is:

Computational Statistics Handbook with MATLAB

Table of Contents. Part I. Deterministic Models... 1

Subject CS1 Actuarial Statistics 1 Core Principles. Syllabus. for the 2019 exams. 1 June 2018

SYLLABUS OF BASIC EDUCATION SPRING 2018 Construction and Evaluation of Actuarial Models Exam 4

Institute of Actuaries of India

Discrete Multivariate Distributions

Supplement Note for Candidates Using. Models for Quantifying Risk, Fourth Edition

Applied Stochastic Processes and Control for Jump-Diffusions

Summary of Formulae for Actuarial Life Contingencies

From Financial Engineering to Risk Management. Radu Tunaru University of Kent, UK

SOCIETY OF ACTUARIES EXAM STAM SHORT-TERM ACTUARIAL MATHEMATICS EXAM STAM SAMPLE QUESTIONS

I Preliminary Material 1

1. You are given the following information about a stationary AR(2) model:

Statistics and Finance

Stochastic Claims Reserving _ Methods in Insurance

[D7] PROBABILITY DISTRIBUTION OF OUTSTANDING LIABILITY FROM INDIVIDUAL PAYMENTS DATA Contributed by T S Wright

Dynamic Copula Methods in Finance

Exam MLC Spring 2007 FINAL ANSWER KEY

Actuarial Mathematics for Life Contingent Risks

Modern Actuarial Risk Theory

A x 1 : 26 = 0.16, A x+26 = 0.2, and A x : 26

May 2001 Course 3 **BEGINNING OF EXAMINATION** Prior to the medical breakthrough, s(x) followed de Moivre s law with ω =100 as the limiting age.

SYLLABUS POST GRADUATE DIPLOMA IN ACTUARIAL SCIENCE P.G. DEPARTMENT OF ACTUARIAL SCIENCE BISHOP HEBER COLLEGE (AUTONOMOUS)

ADVANCED ASSET PRICING THEORY

Implementing Models in Quantitative Finance: Methods and Cases

TABLE OF CONTENTS - VOLUME 2

Chapter 3 Statistical Quality Control, 7th Edition by Douglas C. Montgomery. Copyright (c) 2013 John Wiley & Sons, Inc.

CONTENTS CHAPTER 1 INTEREST RATE MEASUREMENT 1

Solutions to EA-1 Examination Spring, 2001

Martingale Methods in Financial Modelling

4-2 Probability Distributions and Probability Density Functions. Figure 4-2 Probability determined from the area under f(x).

Handbook of Financial Risk Management

Maximum Likelihood Estimates for Alpha and Beta With Zero SAIDI Days

CIA Education Syllabus Approved by the CIA Board on November 26, Revised November 23, Document

November 2012 Course MLC Examination, Problem No. 1 For two lives, (80) and (90), with independent future lifetimes, you are given: k p 80+k

**BEGINNING OF EXAMINATION**

Master s in Financial Engineering Foundations of Buy-Side Finance: Quantitative Risk and Portfolio Management. > Teaching > Courses

Martingale Methods in Financial Modelling

1 Business-Cycle Facts Around the World 1

Monitoring Accrual and Events in a Time-to-Event Endpoint Trial. BASS November 2, 2015 Jeff Palmer

Volatility Models and Their Applications

AMSTERDAM BOSTON HEIDELBERG LONDON NEW YORK OXFORD PARIS SAN DIEGO SAN FRANCISCO SINGAPORE SYDNEY TOKYO Academic Press is an Imprint of Elsevier

Probability and Statistics

May 2012 Course MLC Examination, Problem No. 1 For a 2-year select and ultimate mortality model, you are given:

Post - Graduate Programme in Actuarial Science. Courses of study, Schemes of Examinations & Syllabi (Choice Based Credit System)

Module 2 caa-global.org

Stochastic Analysis Of Long Term Multiple-Decrement Contracts

Homework Problems Stat 479

Homework Problems Stat 479

Homework Problems Stat 479

RECURSIVE VALUATION AND SENTIMENTS

2017 IAA EDUCATION GUIDELINES

Appendix A. Selecting and Using Probability Distributions. In this appendix

ACTL5105 Life Insurance and Superannuation Models. Course Outline Semester 1, 2016

In physics and engineering education, Fermi problems

Introduction Recently the importance of modelling dependent insurance and reinsurance risks has attracted the attention of actuarial practitioners and

A Comprehensive, Non-Aggregated, Stochastic Approach to. Loss Development

M.Sc. ACTUARIAL SCIENCE. Term-End Examination

Market Risk Analysis Volume IV. Value-at-Risk Models

Gujarat University Choice Based Credit System (CBCS) Syllabus for Statistics (UG) B. Sc. Semester III and IV Effective from June, 2018.

Chapter 8 Sequences, Series, and the Binomial Theorem

MAP AUPHA. Health Administration Press, Chicago, Illinois. Association of University Programs in Health Administration, Arlington, Virginia

St. Xavier s College Autonomous Mumbai T.Y.B.A. Syllabus For 5 th Semester Courses in Statistics (June 2016 onwards)

Certified Quantitative Financial Modeling Professional VS-1243

FINANCIAL DERIVATIVE. INVESTMENTS An Introduction to Structured Products. Richard D. Bateson. Imperial College Press. University College London, UK

b g is the future lifetime random variable.

Sequences, Series, and Probability Part I

SOCIETY OF ACTUARIES/CASUALTY ACTUARIAL SOCIETY EXAM C CONSTRUCTION AND EVALUATION OF ACTUARIAL MODELS EXAM C SAMPLE QUESTIONS

Introduction to Loss Distribution Approach

NCCI s New ELF Methodology

Statistical Modeling Techniques for Reserve Ranges: A Simulation Approach

Transcription:

MODELS FOR QUANTIFYING RISK THIRD EDITION ROBIN J. CUNNINGHAM, FSA, PH.D. THOMAS N. HERZOG, ASA, PH.D. RICHARD L. LONDON, FSA B 360811 ACTEX PUBLICATIONS, INC. WINSTED, CONNECTICUT

PREFACE iii THIRD EDITION PREFACE vii PART ONE: REVIEW AND BACKGROUND MATERIAL CHAPTER 1 REVIEW OF INTEREST THEORY 3 1.1 Interest Measures 3 1.2 Level Annuity Functions 7 1.2.1 Immediate Annuity 7 1.2.2 Annuity-due 8 1.2.3 Continuous Annuity 9 1.3 Non-Level Annuity Functions 11 1.3.1 Immediate Annuities 11 1.3.2 Annuities-due 13 1.3.3 Continuous Annuities 15 1.4 Equation of Value 17 CHAPTER 2 REVIEW OF PROBABILITY 19 2.1 Random Variables and Their Distributions 19 2.1.1 Discrete Random Variables 20 2.1.2 Continuous Random Variables 23 2.1.3 Mixed Random Variables 25 2.1.4 More on Moments of Random Variables 25 2.2 Survey of Particular Discrete Distributions 27 2.2.1 The Discrete Uniform Distribution 27 2.2.2 The Binomial Distribution 28 2.2.3 The Negative Binomial Distribution 28 2.2.4 The Geometric Distribution 30 2.2.5 The Poisson Distribution 30 ix

2.3 Survey of Particular Continuous Distributions 31 2.3.1 The Continuous Uniform Distribution 31 2.3.2 The Normal Distribution 32 2.3.3 The Exponential Distribution 34 2.3.4 The Gamma Distribution 35 2.4 Multivariate Probability 36 2.4.1 The Discrete Case 36 2.4.2 The Continuous Case 39 2.5 Sums of Independent Random Variables 41 2.5.1. The Moments of S 41 2.5.2 Distributions Closed Under Convolution 42 2.5.3 The Method of Convolutions 44 2.5.4 Approximating the Distribution of S 45 2.6 Compound Distributions 45-2.6.1 The Moments of S 46 2.6.2 The Compound Poisson Distribution 48 PART TWO: MODELS FOR SURVIVAL-CONTINGENT RISKS CHAPTER 3 SURVIVAL MODELS ^ (CONTINUOUS PARAMETRIC CONTEXT) 51 3.1 The Age-at-Failure Random Variable 51 3.1.1 The Cumulative Distribution Function of X 53 3.1.2 The Survival Distribution Function of X 53 3.1.3 The Probability Density Function of X 54 3.1.4 The Hazard Rate Function of X 55 3.1.5 The Moments of the Age-at-Failure Random Variable X 57 3.1.6 Actuarial Survival Models 58 3.2 Examples of Parametric Survival Models 60 3.2.1 The Uniform Distribution 60 3.2.2 The Exponential Distribution 61 3.2.3 The Gompertz Distribution 62 3.2.4 The Makeham Distribution 62 3.2.5 The Weibull Distribution 63 3.2.6 Summary of Parametric Survival Models 63 3.3 The Time-to-Failure Random Variable 64 3.3.1 The Survival Distribution Function of T x 65 3.3.2 The Cumulative Distribution Function of T x 66

XI 3.4 3.5 3.6 3.3.3 The Probability Density Function of T x 67 3.3.4 The Hazard Rate Function of T x 68 3.3.5 Moments of the Future Lifetime Random Variable T x 68 3.3.6 The Time-to-Failure Random Variable K x 71 The Central Rate 73 Select Survival Models 75 Exercises 76 CHAPTER 4 THE LIFE TABLE (DISCRETE TABULAR CONTEXT) 81 4.1 Definition of the Life Table 81 4.2 The Traditional Form of the Life Table 83 4.3 Other Functions Derived from l x 85 4.3.1 The Force of Failure 86 4.3.2 The Probability Density Function of X 88 4.3.3 Conditional Probabilities and Densities 90 4.3.4 The Curtate Expectation of Life 94 4.3.5 The Central Rate 96 4.4 Summary of Concepts and Notation 97 4.5 Methods for Non-Integral Ages 97 4.5.1 Linear Form for x+t 100 4.5.2 Exponential Form for x+t 104 4.5.3 Hyperbolic Form for x+t 106 4.5.4 Summary 108 4.6 Select Life Tables 109 4.7 Life Table Summary 112 4.8 Exercises 113 CHAPTER 5 CONTINGENT PAYMENT MODELS (INSURANCE MODELS) 121 5.1 Discrete Stochastic Models 122 5.1.1 The Discrete Random Variable for Time of Failure 122 5.1.2 The Present Value Random Variable 122 5.1.3 Modifications of the Present Value Random Variable 126 5.1.4 Applications to Life Insurance 131

xii TABLE OF CONTENTS 5.2 Group Deterministic Approach 135 5.3 Continuous Stochastic Models 138 5.3.1 The Continuous Random Variable for Time to Failure 138 5.3.2 The Present Value Random Variable 139 5.3.3 Modifications of the Present Value Random Variable 141 5.3.4 Applications to Life Insurance 141 5.3.5 Continuous Functions Evaluated from Parametric Survival Models 142 5.4 Contingent Payment Models with Varying Payments 145 5.5 Continuous and m' hly Functions Approximated from the Life Table 148 5.5.1 Continuous Contingent Payment Models 148 5.5.2 m' hly Contingent Payment Models 151 5.6 Miscellaneous Examples 153 5.7 Exercises 156 CHAPTER 6 CONTINGENT ANNUITY MODELS (LIFE ANNUITIES) 161 6.1 Whole Life Annuity Models 162 6.1.1 The Immediate Case 163 6.1.2 The Due Case 169 6.1.3 The Continuous Case 171 6.2 Temporary Annuity Models 174 6.2.1 The Immediate Case 174 6.2.2 The Due Case 179 6.2.3 The Continuous Case 182 6.3 Deferred Whole Life Annuity Models 185 6.3.1 The Immediate Case 185 6.3.2 The Due Case 187 6.3.3 The Continuous Case 188 6.4 Contingent Annuities Payable m My 191 6.4.1 The Immediate Case 191 6.4.2 The Due Case 192 6.4.3 Random Variable Analysis 193 6.4.4 Numerical Evaluation in the m thly and Continuous Cases 195 6.5 Non-Level Payment Annuity Functions 197 6.6 Miscellaneous Examples 198 6.7 Exercises 203

CHAPTER 7 7.1 7.2 7.3 7.4.7.5 7.6 7.7 CHAPTER 8 FUNDING PLANS FOR CONTINGENT CONTRACTS (ANNUAL PREMIUMS) 211 Annual Funding Schemes for Contingent Payment Models 212 7.1.1 Discrete Contingent Payment Models 212 7.1.2 Continuous Contingent Payment Models 217 7.1.3 Contingent Annuity Models 218 7.1.4 Non-Level Premium Contracts 218 Random Variable Analysis 219 Continuous Payment Funding Schemes 224 7.3.1 Discrete Contingent Payment Models 224 7.3.2 Continuous Contingent Payment Models 225 Funding Schemes with m Wy Payments 228 Funding Plans Incorporating Expenses 230 Miscellaneous Examples 233 Exercises 240 CONTINGENT CONTRACT RESERVES (BENEFIT RESERVES) 245 8.1 Reserves for Contingent Payment Models with Annual Payment Funding 247 8.1.1 Reserves by the Prospective Method 247 8.1.2 Reserves by the Retrospective Method 250 8.1.3 Additional Terminal Reserve Expressions 253 8.1.4 Random Variable Analysis 255 8.1.5 Reserve for Contingent Contracts with Immediate Payment of Claims 257 8.1.6 Reserves for Contingent Annuity Models 258 8.2 Recursive Relationships for Discrete Models with Annual Premiums 259 8.2.1 Group Deterministic Approach 259 8.2.2 Random Variable Analysis - Cash Basis 263 8.2.3 Random Variable Analysis - Accrued Basis 266 8.3 Reserves for Contingent Payment Models with Continuous Payment Funding 270 8.3.1 Discrete Whole Life Contingent Payment Models 270 8.3.2 Continuous Whole Life Contingent Payment Models 271 8.3.3 Random Variable Analysis 275

xiv TABLE OF CONTENTS 8.4 Reserves for Contingent Payment Models with m' hly Payment Funding 276 8.5 Incorporation of Expenses 279 8.6 Reserves at Fractional Durations 280 8.7 Generalization to Non-Level Benefits and Premiums 282 8.7.1 Discrete Models 282 8.7.2 Continuous Models 286 8.8 Miscellaneous Examples 288 8.9 Exercises 292 CHAPTER 9 MODELS DEPENDENT ON MULTIPLE SURVIVALS (MULTI-LIFE MODELS) 299 9.1 The Joint-Life Model 299 s 9.1.1 The Time-to-Failure Random Variable for a Joint-Life Status 300 9.1.2 Survival Distribution Function of T xy 300 9.1.3 Cumulative Distribution Function of T^ 300 9.1.4 Probability Density Function of T xy 302 9.1.5 Hazard Rate Function of T^ 303 9.1.6 Conditional Probabilities 303 9.1.7 Moments of T xv 305 9.2 The Last-Survivor Model 306 9.2.1 The Time-to-Failure Random Variable for a Last-Survivor Status 306 9.2.2 Functions of the Random Variable T w 307 9.2.3 Relationships Between T xy and T^ 310 9.3 Contingent Probability Functions 311 9.4 Contingent Contracts Involving Multi-Life Statuses 314 9.4.1 Contingent Payment Models 314 9.4.2 Contingent Annuity Models 316 9.4.3 Annual Premiums and Reserves 317 9.4.4 Reversionary Annuities 319 9.4.5 Contingent Insurance Functions 321 9.5 General Random Variable Analysis 322 9.5.1 Marginal Distributions of T x and T y 322 9.5.2 TheCovarianceofr x and7; 323 9.5.3 Other Joint Functions of T x and T y 325 9.5.4 Joint and Last-Survivor Status Functions 328 9.6 Common Shock - A Model for Lifetime Dependency 330 9.7 Exercises 333

XV CHAPTER 10 MULTIPLE CONTINGENCIES WITH APPLICATIONS (MULTIPLE-DECREMENT MODELS) 339 10.1 Discrete Multiple-Decrement Models 339 10.1.1 The Multiple-Decrement Table 341 10.1.2 Random Variable Analysis 344 10.2 Theory of Competing Risks 346 10.3 Continuous Multiple-Decrement Models 347 10.4 Uniform Distribution of Decrements 352 10.4.1 Uniform Distribution in the Multiple-Decrement Context 352 10.4.2 Uniform Distribution in the Associated Single- Decrement Tables 354 10.5 Actuarial Present Value 357 10.6 Asset Shares 363 10.7 Multi-State Models 366 10.7.1 The Homogeneous Process 366 10.7.2 The Nonhomogeneous Process 372 10.8 Exercises 374 PART THREE: MODELS FOR NON-SURVIVAL-CONTINGENT RISKS CHAPTER 11 CLAIM FREQUENCY MODELS 383 11.1 Section 2.2 (Discrete Distributions) Revisited 383 11.1.1 The Binomial Distribution 383 11.1.2 The Poisson Distribution 384 11.1.3 The Negative Binomial Distribution 389 11.1.4 The Geometric Distribution 393 11.1.5 Summary of the Recursive Relationships 393 11.1.6 Probability Generating Functions 394 11.2 Creating Additional Counting Distributions 397 11.2.1 Compound Frequency Models 397 11.2.2 Mixture Frequency Models 402 11.2.3 Truncation or Modification at Zero 405 11.3 Counting Processes 409 11.3.1 Properties of Counting Processes 410 11.3.2 The Poisson Counting Process 411

xvi TABLE OF CONTENTS 11.3.3 Further Properties of the Poisson Counting Process 412 11.3.4 Poisson Mixture Processes 415 11.3.5 The Nonstationary Poisson Counting Process 415 11.4 Exercises 418 CHAPTER 12 CLAIM SEVERITY MODELS 425 12.1 Fundamental Continuous Distributions 426 12.1.1 The Normal and Exponential Distributions 426 12.1.2 The Pareto Distribution 426 12.1.3 Analytic Measures of Tail Weight 429 12.2 Generating New Distributions 431 12.2.1 Summation 431, 12.2.2 Scalar Multiplication 431 12.2.3 Power Operations 434 12.2.4 Exponentiation and the Lognormal Distribution 437 12.2.5 Summary of Severity Distributions 439 12.2.6 Mixtures of Distributions 442 12.2.7 Spliced Distributions 448 12.2.8 Limiting Distributions 450 12.3 Modifications of the Loss Random Variable 451 12.3.1 Deductibles 452 12.3.2 Policy Limits 454 12.3.3 Relationships between Deductibles and Policy Limits 457 12.3.4 Coinsurance Factors 460 12.3.5 The Effect of Inflation 461 12.3.6 Effect of Coverage Deductibles on Frequency Models 463 12.4 Tail Weight Revisited; Risk Measures 470 12.4.1 The Mean Excess Loss Function 471 12.4.2 Conditional Tail Expectation 474 12.4.3 Value at Risk 475 12.4.4 Distortion Risk Measures 476 12.4.5 Risk Measures Using Discrete Distributions 479 12.4.6 Other Risk Measures 481 12.5 Empirical Loss Distributions 481 12.6 Exercises 485

xvu CHAPTER 13 MODELS FOR AGGREGATE PAYMENTS 495 13.1 Individual Risk versus Collective Risk 495 13.2 Selection of Frequency and Severity Distributions 499 13.2.1 Frequency 499 13.2.2 Severity 500 13.2.3 Frequency-Severity Interaction 501 13.3 More on the Collective Risk Model 502 13.3.1 Convolutions of the Probability Function ofx 502 13.3.2 Convolutions of the CDF ofx 508 13.3.3 Continuous Severity Distributions 512 13.3.4 A Final Thought Regarding Convolutions 519 13.4 Effect of Coverage Modifications 520 13.4.1 Modifications Applied to Individual Losses 521 13.4.2 Modifications Applied to the Aggregate Loss (Stop-Loss Reinsurance) 523 13.5 Infinitely Divisible Distributions 528 13.5.1 Definition of Infinite Divisibility 528 13.5.2 The Poisson Distribution 529 13.5.3 The Negative Binomial Distribution 529 13.6 Exercises 529 CHAPTER 14 PROCESS MODELS 537 14.1 The Compound Poisson Process 537 14.1.1 Moments of the Compound Poisson Process 538 14.1.2 Other Properties of the Compound Poisson Process 539 14.2 The Surplus Process Model 540 14.3 The Probability of Ruin 543 14.3.1 The Adjustment Coefficient 544 14.3.2 The Probability of Ruin 547 14.4 The Distribution of Surplus Deficit 550 14.4.1 The Event of U{t) <u 550 14.4.2 The Cumulative Loss of Surplus 553 14.5 Probability of Ruin in Finite Time 557 14.6 Exercises 558

xviii TABLE OF CONTENTS APPENDIX A REVIEW OF MARKOV CHAINS 565 APPENDIX B REVIEW OF STOCHASTIC SIMULATION 587 APPENDIX C EVALUATION BY SIMULATION 605 APPENDIX D USING MICROSOFT EXCEL AND VISUAL BASIC MACROS TO COMPUTE ACTUARIAL FUNCTIONS 625 APPENDIX E REVIEW OF THE INCOMPLETE GAMMA FUNCTION 641 ANSWERS TO TEXT EXERCISES 649 BIBLIOGRAPHY 671 INDEX 673