The death data and the census data dont match let

Info iconThis preview shows page 1. Sign up to view the full content.

View Full Document Right Arrow Icon
This is the end of the preview. Sign up to access the rest of the document.

Unformatted text preview: aths, and give the range of ages of the lives at the beginning of the rate interval. Determine the value of f , stating any assumptions you make. Actuarial Statistics – Module 7: Exposed to risk Examples Calendar year rate intervals Solution I 1 2 Everybody changes age label on the same day-1 Jan. This is a calendar year rate interval. The actual age of a person with age label x on Jan 1, must between x (birthday is on 1 Jan) and x + 1 (birthday is on 31 Dec). The death data and the census data don’t match. Let time 0 = 1 Jan 2006 time 1 = 1 Jan 2007 27/35 Actuarial Statistics – Module 7: Exposed to risk Examples Calendar year rate intervals Solution II Px (t )=no. of lives at time t aged x last birthday at the previous or coincident 1 Jan. Then 1 c Ex = Px (t )dt 0 = = 1 (P (1 Jan 2006) + Px (Just before 1 Jan 2007)) 2x 1 1 (Px (0) + Px +1 (1 Jan 2007)) = (Px (0) + Px +1 (1)) 2 2 Note from definition: Px (0)=no. of lives at time 0 (1 Jan 2006) aged x last birthday at the previous or coincident 1 Jan. Px (0)=no. of lives on 1 Jan 2006+0 aged x next birthday. 28/35 Actuarial Statistics – Module 7: Exposed to risk Examples Calendar year rate intervals Solution III Noting that age x last birthday is same as age x + 1 next birthday yields Px (0) = Px +1 (0) The same logic implies Px +1 (1) = Px +2 (1) So finally 3 29/35 1 c Ex = (Px +1 (0) + Px +2 (1)) 2 From 1. we know the range of ages at the start of the rate interval is (x , x + 1). Hence, the average age at the start of d 1 the rate interval is x + 2 and µx = Exc estimates ˆ x µ(x + 1 )+ 1 = µx +1 . This means f = 1. 2 2 We assumed that the birthdays are uniformly spread across the calendar. Actuarial Statistics – Module 7: Exposed to risk Examples Policy year rate intervals 1 Introduction Central vs Initial Exposed to Risk Complete data Incomplete data 2 Census approximations Introduction “Calendar Year” rate interval “Policy Year” rate interval 3 Examples Definition of x Trapezium approximation Estimation Principle of correspondence Calendar year rate intervals Policy year rate intervals 30/35 Actuarial Statistics – Module 7: Exposed to risk Examples Policy year rate intervals Example Consider the age definition “age next birthday at the policy anniversary preceding death”. Determine 1 the minimum/maximum possible actual ages at the start of the rate interval 2 the average actual age at the start of the rate interval. The definition of age gives rise to a policy year rate interval starting on the policy anniversary: 1 2 30/35 At the start of the rate interval, actual ages range from x − 1 (those lives with x th birthdays occur in a year’s time, just before the next policy anniversary) to x (those lives with x th birthdays occur immediately after the policy anniversary) Assuming birthdays are distributed uniformly over policy years, average actual age at start of the rate interval is x − 1 . 2 Actuarial Statistics – Module 7: Exposed to risk Examples Policy year rate intervals Example of exam question An...
View Full Document

This document was uploaded on 04/03/2014.

Ask a homework question - tutors are online