13_AS_6_lec_a

We can then modify the initial exposed to risk to a

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

This is the end of the preview. Sign up to access the rest of the document.

Unformatted text preview: state models 15/30 Actuarial Statistics – Module 6: Parametric models: Binomial and Poisson models Binomial model Central exposed to risk Central exposed to risk Sometimes we actually know when deaths occur, say x + ti . We can then modify the initial exposed to risk to a central exposed to risk N c Ex (bi − ai ) (1 − di ) + = i =1 (ti − ai ) di i =1 where deaths contribute the period of length (ti − ai ) from x + ai to x + ti survivors contribute the period of length (bi − ai ) from x + ai to x + bi . c Note Ex = v is also called the observed total waiting at age x . 15/30 Actuarial Statistics – Module 6: Parametric models: Binomial and Poisson models Binomial model Central exposed to risk c When the exact times of deaths are not available, but Ex is, the usual approch is to assume that deaths occur on average at age x + 1 so that the actuarial estimate becomes 2 qx = c Ex d + d 2 because under that assumption c Ex = Ex + d . 2 Proof: N Ex (1 − ai ) + = i :Di =1 (bi − ai ) i ;Di =0 N (1 − ti + ti − ai ) + = i :Di =1 16/30 (bi − ai ) i ;Di =0 Actuarial Statistics – Module 6: Parametric models: Binomial and Poisson models Binomial model Central exposed to risk N (1 − ti + ti − ai ) di + = i =1 N N (1 − ti ) di + = i =1 N = = 17/30 (bi − ai ) (1 − di ) i (ti − ai ) di + i =1 i N c (1 − ti ) di + Ex = i =1 c Ex + 1− i =1 d /2 (bi − ai ) (1 − di ) 1 2 c di + Ex Actuarial Statistics – Module 6: Parametric models: Binomial and Po...
View Full Document

This document was uploaded on 04/03/2014.

Ask a homework question - tutors are online