Aggregate Loss Models



Similar documents
Approximation of Aggregate Losses Using Simulation

Math 461 Fall 2006 Test 2 Solutions

A LOGNORMAL MODEL FOR INSURANCE CLAIMS DATA

Probability Generating Functions

Joint Exam 1/P Sample Exam 1

3. The Economics of Insurance

Overview of Monte Carlo Simulation, Probability Review and Introduction to Matlab

Computation of the Aggregate Claim Amount Distribution Using R and actuar. Vincent Goulet, Ph.D.

Chapter 4 Lecture Notes

e.g. arrival of a customer to a service station or breakdown of a component in some system.

MAS108 Probability I

Lecture 8. Confidence intervals and the central limit theorem

Math 151. Rumbos Spring Solutions to Assignment #22

Random variables P(X = 3) = P(X = 3) = 1 8, P(X = 1) = P(X = 1) = 3 8.

Statistics 100A Homework 8 Solutions

MATH4427 Notebook 2 Spring MATH4427 Notebook Definitions and Examples Performance Measures for Estimators...

ECE302 Spring 2006 HW5 Solutions February 21,

Lecture Notes 1. Brief Review of Basic Probability

Lloyd Spencer Lincoln Re

Lecture 6: Discrete & Continuous Probability and Random Variables

6.041/6.431 Spring 2008 Quiz 2 Wednesday, April 16, 7:30-9:30 PM. SOLUTIONS

UNIT I: RANDOM VARIABLES PART- A -TWO MARKS

Math 370/408, Spring 2008 Prof. A.J. Hildebrand. Actuarial Exam Practice Problem Set 5 Solutions

Math 370/408, Spring 2008 Prof. A.J. Hildebrand. Actuarial Exam Practice Problem Set 2 Solutions

Math 431 An Introduction to Probability. Final Exam Solutions

The Exponential Distribution

Errata and updates for ASM Exam C/Exam 4 Manual (Sixteenth Edition) sorted by page

5. Continuous Random Variables

ECE302 Spring 2006 HW4 Solutions February 6,

For a partition B 1,..., B n, where B i B j = for i. A = (A B 1 ) (A B 2 ),..., (A B n ) and thus. P (A) = P (A B i ) = P (A B i )P (B i )

Stats on the TI 83 and TI 84 Calculator

STAT 315: HOW TO CHOOSE A DISTRIBUTION FOR A RANDOM VARIABLE

Statistics 100A Homework 7 Solutions

1 Prior Probability and Posterior Probability

ISyE 6761 Fall 2012 Homework #2 Solutions

INSURANCE RISK THEORY (Problems)

Final Mathematics 5010, Section 1, Fall 2004 Instructor: D.A. Levin

Tenth Problem Assignment

Maximum Likelihood Estimation

Exam C, Fall 2006 PRELIMINARY ANSWER KEY

A Uniform Asymptotic Estimate for Discounted Aggregate Claims with Subexponential Tails

Math/Stats 342: Solutions to Homework

Dongfeng Li. Autumn 2010

AGGREGATE CLAIMS, SOLVENCY AND REINSURANCE. David Dickson, Centre for Actuarial Studies, University of Melbourne. Cherry Bud Workshop

Lecture 3: Continuous distributions, expected value & mean, variance, the normal distribution

Notes on Continuous Random Variables

STA 256: Statistics and Probability I

Practice problems for Homework 11 - Point Estimation

SF2940: Probability theory Lecture 8: Multivariate Normal Distribution

Chapter 4 - Lecture 1 Probability Density Functions and Cumul. Distribution Functions

Exponential Distribution

1 Sufficient statistics

Poisson processes (and mixture distributions)

MASSACHUSETTS INSTITUTE OF TECHNOLOGY 6.436J/15.085J Fall 2008 Lecture 14 10/27/2008 MOMENT GENERATING FUNCTIONS

2WB05 Simulation Lecture 8: Generating random variables

Lectures on Stochastic Processes. William G. Faris

What is Statistics? Lecture 1. Introduction and probability review. Idea of parametric inference

Probability and Statistics Prof. Dr. Somesh Kumar Department of Mathematics Indian Institute of Technology, Kharagpur

Manual for SOA Exam MLC.

Discrete Mathematics and Probability Theory Fall 2009 Satish Rao, David Tse Note 18. A Brief Introduction to Continuous Probability

Notes on the Negative Binomial Distribution

( ) is proportional to ( 10 + x)!2. Calculate the

Probability Distribution for Discrete Random Variables

Practice Problems for Homework #6. Normal distribution and Central Limit Theorem.

Mathematics of Risk. Introduction. Case Study #1 Personal Auto Insurance Pricing. Mathematical Concepts Illustrated. Background

An Introduction to Basic Statistics and Probability

Premium Calculation - continued

Department of Mathematics, Indian Institute of Technology, Kharagpur Assignment 2-3, Probability and Statistics, March Due:-March 25, 2015.

SF2940: Probability theory Lecture 8: Multivariate Normal Distribution

0 x = 0.30 x = 1.10 x = 3.05 x = 4.15 x = x = 12. f(x) =

2. Discrete random variables

University of California, Los Angeles Department of Statistics. Random variables

Math 370, Actuarial Problemsolving Spring 2008 A.J. Hildebrand. Practice Test, 1/28/2008 (with solutions)

Section 5.1 Continuous Random Variables: Introduction

Homework 4 - KEY. Jeff Brenion. June 16, Note: Many problems can be solved in more than one way; we present only a single solution here.

Important Probability Distributions OPRE 6301

IEOR 6711: Stochastic Models I Fall 2012, Professor Whitt, Tuesday, September 11 Normal Approximations and the Central Limit Theorem

Portfolio Distribution Modelling and Computation. Harry Zheng Department of Mathematics Imperial College

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

IEOR 6711: Stochastic Models, I Fall 2012, Professor Whitt, Final Exam SOLUTIONS

Definition: Suppose that two random variables, either continuous or discrete, X and Y have joint density

Math 370, Spring 2008 Prof. A.J. Hildebrand. Practice Test 2 Solutions

Statistics 100A Homework 4 Solutions

. (3.3) n Note that supremum (3.2) must occur at one of the observed values x i or to the left of x i.

4. Continuous Random Variables, the Pareto and Normal Distributions

Chapter 3: DISCRETE RANDOM VARIABLES AND PROBABILITY DISTRIBUTIONS. Part 3: Discrete Uniform Distribution Binomial Distribution

Solution. Let us write s for the policy year. Then the mortality rate during year s is q 30+s 1. q 30+s 1

Annuities. Lecture: Weeks Lecture: Weeks 9-11 (STT 455) Annuities Fall Valdez 1 / 43

Lecture 7: Continuous Random Variables

Master s Theory Exam Spring 2006

STAT 830 Convergence in Distribution

THE NUMBER OF GRAPHS AND A RANDOM GRAPH WITH A GIVEN DEGREE SEQUENCE. Alexander Barvinok

ECE302 Spring 2006 HW3 Solutions February 2,

MATH2740: Environmental Statistics

Premium calculation. summer semester 2013/2014. Technical University of Ostrava Faculty of Economics department of Finance

How To Find Out How Much Money You Get From A Car Insurance Claim

The sample space for a pair of die rolls is the set. The sample space for a random number between 0 and 1 is the interval [0, 1].

Transcription:

Aggregate Loss Models Chapter 9 Stat 477 - Loss Models Chapter 9 (Stat 477) Aggregate Loss Models Brian Hartman - BYU 1 / 22

Objectives Objectives Individual risk model Collective risk model Computing the aggregate loss models Approximate methods Effect of policy modifications Chapter 9 (sections 9.1-9.7; exclude 9.6.1 and examples 9.9 and 9.11) Assignment: read section 9.7 Chapter 9 (Stat 477) Aggregate Loss Models Brian Hartman - BYU 2 / 22

Individual risk model Individual risk model Consider a portfolio of n insurance policies. Denote the loss, for a fixed period, for each policy i by X i, for i = 1,..., n. Assume these lossses are independent and (possibly) identically distributed. The aggregate loss, S, is defined by the sum of these losses: S = X 1 + X 2 + + X n. It is possible that here a policy does not incur a loss so that each X i has a mixed distribution with a probability mass at zero. Chapter 9 (Stat 477) Aggregate Loss Models Brian Hartman - BYU 3 / 22

Individual risk model Alternative representation Alternative representation Assume that the losses are also identically distributed say as X. Then we can write X as the product of a Bernoulli I and a positive (continuous) random variable Y : X = IY I = 1 indicates there is a claim, otherwise I = 0 means no claim. Let Pr(I = 1) = q and hence Pr(X = 0) = 1 q. In addition, assume E(Y ) = µ Y and Var(Y ) = σ 2 Y. Typically it is assumed that I and Y are independent so that E(X) = E(I)E(Y ) = qµ Y and Var(X) = q(1 q)µ 2 Y + qσ 2 Y. Chapter 9 (Stat 477) Aggregate Loss Models Brian Hartman - BYU 4 / 22

Individual risk model Mean and variance Mean and variance in the individual risk model The mean of the aggregate loss can thus be written as and its variance is E(S) = nqµ Y Var(S) = nq(1 q)µ 2 Y + nqσ 2 Y. Example: Consider a portfolio on 1,000 insurance policies where each policy has a probability of a claim of 0.15. When a claim occurs, the amount of claim has a Pareto distribution with parameters α = 3 and θ = 100. Calculate the mean and variance of the aggregate loss. Chapter 9 (Stat 477) Aggregate Loss Models Brian Hartman - BYU 5 / 22

Individual risk model Illustrative examples Illustrative examples Example 1: An insurable event has a 10% probability of occurring and when it occurs, the amount of the loss is exactly 1,000. Market research has indicated that consumers will pay at most 115 for insuring this event. How many policies must a company sell in order to have a 95% chance of making money (ignoring expenses)? Assume Normal approximation. Example 2: Exercise 9.20 of textbook. Chapter 9 (Stat 477) Aggregate Loss Models Brian Hartman - BYU 6 / 22

Individual risk model Exact distribution using convolution Exact distribution of S using convolution Consider the case of S = X 1 + X 2. The density of S can be computed using convolution as: f 2 (s) = f S (s) = s 0 f 1 (s y)f 2 (y)dy = s 0 f 2 (s y)f 1 (y)dy To extend to n dimension, do it recursively. Let f (n 1) (s) be the (n 1)-th convolution so that f n (s) = f S (s) = = s 0 s 0 f (n 1) (s y)f n (y)dy f n (s y)f (n 1) (y)dy Chapter 9 (Stat 477) Aggregate Loss Models Brian Hartman - BYU 7 / 22

Individual risk model Mixed random variable The case of the mixed random variable Often, X i has a probability mass at zero so that its density function is given by { qi, for x = 0, f i (x) = (1 q i )f Y (x), for x > 0, where f Y ( ) is a legitimate density function of a positive continuous random variable. Here, q i is interpreted as the probability that the loss is zero. In this case, use the cumulative distribution function: F 2 (s) = F S (s) = s 0 F 1 (s y)df 2 (y) = To extend to n dimension, do it recursively. s 0 F 2 (s y)df 1 (y) Chapter 9 (Stat 477) Aggregate Loss Models Brian Hartman - BYU 8 / 22

Individual risk model The case of the Exponential The case of the Exponential distribution Consider the case where X i has the density function expressed as { 0.10, for x = 0, f i (x) = 0.90f Y (x), for x > 0, where Y is an Exponential with mean 1, for i = 1, 2. Derive expressions for the density and distribution functions of the sum S = X 1 + X 2. Chapter 9 (Stat 477) Aggregate Loss Models Brian Hartman - BYU 9 / 22

Individual risk model Approximation by CLT Approximating the individual risk model For large n, according to the Central Limit Theorem, S can be approximated with a Normal distribution. Use the results on slides p. 5 to compute the mean and the variance of the aggregate loss S in the individual risk model. Then, probabilities can be computed using Normal as follows: [ ] S E(S) Pr(S s) = Pr S E(S) Var(S) Var(S) Pr = Φ [ ] Z S E(S) Var(S) ( ) S E(S) Var(S) Chapter 9 (Stat 477) Aggregate Loss Models Brian Hartman - BYU 10 / 22

Individual risk model Illustrative example Illustrative example 1 An insurer has a portfolio consisting of 25 one-year life insurance policies grouped as follows: Insured amount b k Number of policies n k 1 10 2 5 3 10 The probability of dying within one year is q k = 0.01 for each insured, and the policies are independent. The insurer sets up an initial capital of $1 to cover its future obligations. Using Normal approximation, calculate the probability that the insurer will be able to meet its financial obligation. Chapter 9 (Stat 477) Aggregate Loss Models Brian Hartman - BYU 11 / 22

Collective risk model Collective risk model Let X i be the claim payment made for the ith policyholder and let N be the random number of claims. The insurer s aggregate loss is S = X 1 + + X N = N X i. i=1 This is called the Collective Risk Model. If N, X 1, X 2,... are independent and the individual claims X i are i.i.d., then S has a compound distribution. N: frequency of claims; X: the severity of claims. Central question is finding the probability distribution of S. Chapter 9 (Stat 477) Aggregate Loss Models Brian Hartman - BYU 12 / 22

Collective risk model Properties Properties of the collective risk model X is called the individual claim and assume has moments denoted by µ k = E(X k ). Mean of S: E(S) = E(X)E(N) = µ 1 E(N) Variance of S: Var(S) = E(N)Var(X) + Var(N)µ 2 1 MGF of S: M S (t) = M N [log M X (t)] PGF of S: P S (t) = P N [P X (t)] CDF of S: Pr(S s) = n=0 Pr(S s N = n)pr(n = n) Chapter 9 (Stat 477) Aggregate Loss Models Brian Hartman - BYU 13 / 22

Collective risk model Exponential/Geometric Example - Exponential/Geometric Suppose X i Exp(1) and N Geometric(p). MGF of N: M N (t) = Mean of S: E(S) = q/p p 1 qe t ; MGF of X: M X(t) = 1 1 t Variance of S: Var(S) = q/p + q/p 2 = (q/p)(1 + 1/p) p MGF of S: M S (t) = 1 qm X (t) = p 1 q/(1 t) = p + q p p t Observe that the mgf of S can be written as a weighted average: p mgf of r.v. 0 + q mgf of Exp(p) r.v. Thus, F S (s) = p + q(1 e ps ) = 1 qe ps for s > 0. Chapter 9 (Stat 477) Aggregate Loss Models Brian Hartman - BYU 14 / 22

Collective risk model Poisson number of claims Poisson number of claims If N Poisson(λ), so that λ is the average number of claims, then the resulting distribution of S is called a Compound Poisson. MGF of N: M N (t) = exp [ λ ( e t 1 )] It can then be shown that: Mean of S: E(S) = λe(x) = λµ 1 Variance of S: Var(S) = λe(x 2 ) = λµ 2 MGF of S: M S (t) = exp [λ (M X (t) 1)] Chapter 9 (Stat 477) Aggregate Loss Models Brian Hartman - BYU 15 / 22

Collective risk model Illustrative example Illustrative example 2 Suppose S has a compound Poisson distribution with λ = 0.8 and individual claim amount distribution x Pr(X = x) 1 0.250 2 0.375 3 0.375 Compute f S (s) = Pr(S = s) for s = 0, 1,..., 6. Chapter 9 (Stat 477) Aggregate Loss Models Brian Hartman - BYU 16 / 22

Collective risk model Panjer s recursion formula Panjer s recursion formula Let aggregate claims S have a compound distribution with integer-valued non-negative claims with pdf p(x) for x = 0, 1, 2,.... Let the probability of n claims satisfies the recursion relation p k = (a + b n )p k 1 for k = 1, 2,... for some real a and b. Recall this is the (a, b, 1) class of distribution. Then, for the probability of total claims s, we have f S (s) = 1 1 ap(0) For s = 0, we have f S (0) = s h=1 ( a + bh ) p(h)f S (s h). s { Pr(N = 0), if p(0) = 0 M N [log p(0)], if p(0) > 0. Chapter 9 (Stat 477) Aggregate Loss Models Brian Hartman - BYU 17 / 22

Collective risk model The case of Compound Poisson Panjer s recursion for Compound Poisson This is the case where the number of claims is Poisson. Starting value: With Poisson(λ): f S (0) = { Pr(N = 0), if p(0) = 0 M N [log p(0)], if p(0) > 0. f S (s) = 1 s s λhp(h)f S (s h). h=1 Chapter 9 (Stat 477) Aggregate Loss Models Brian Hartman - BYU 18 / 22

Collective risk model Illustrative example Back to illustrative example 2 Same as previous example, but now we solve using Panjer s recursion. Effectively, the recursion formula boils down to f S (s) = 1 s [0.2f S(s 1) + 0.6f S (s 2) + 0.9f S (s 3)]. [Why??] Initial value is: f S (0) = Pr(N = 0) = e 0.8 = 0.44933. Successive values satisfy: f S (1) = 0.2f S (0) = 0.2e 0.8 = 0.089866 f S (2) = 1 2 [0.2f S(1) + 0.6f S (0)] = 0.32e 0.8 = 0.14379 f S (3) = 1 3 [0.2f S(2) + 0.6f S (1) + 0.9f S (0)] = 0.3613e 0.8 = 0.16236 and f S (4) = 0.0499, f S (5) = 0.04736, and f S (6) = 0.03092. [calculated by hand - verify!] Chapter 9 (Stat 477) Aggregate Loss Models Brian Hartman - BYU 19 / 22

Collective risk model Approximating the compound distribution Use CLT to approximate the compound distribution If the average number of claims is large enough, we may use the Normal approximation to estimate the distribution of S. All you need are the mean and variance of the aggregate loss [slides p. 13] Chapter 9 (Stat 477) Aggregate Loss Models Brian Hartman - BYU 20 / 22

Collective risk model Closed under convolution Compound Poisson is closed under convolution Theorem 9.7 of book. If S 1, S 2,..., S m are independent compound Poisson random variables with Poisson parameters λ i and claim distributions (CDF) F i, for i = 1, 2,..., m, then S = S 1 + S 2 + + S m also has a compound Poisson distribution with parameter λ = λ 1 + λ 2 + + λ m and individual claim (severity) distribution F (x) = m i=1 λ i λ F i(x). You add the number of claim parameters, and the individual claim distribution is a weighted sum. Chapter 9 (Stat 477) Aggregate Loss Models Brian Hartman - BYU 21 / 22

Collective risk model Illustrative example Illustrative example 3 You are given S = S 1 + S 2, where S 1 and S 2 are independent and have compound Poisson distributions with λ 1 = 3 and λ 2 = 2 and individual claim amount distributions: x p 1 (x) p 2 (x) 1 0.25 0.10 2 0.75 0.40 3 0.00 0.40 4 0.00 0.10 Determine the mean and variance of the individual claim amount for S. Chapter 9 (Stat 477) Aggregate Loss Models Brian Hartman - BYU 22 / 22