Hurlimann Flashcards
mk
expected loss ratio in development period k, increm LR
sum of incremental paid over sum of prem
=E[sum(Sik)]/sum(Vi)
pi
loss ratio payout factor
loss ratio lag-factor
proportion of total ult expected to be paid in development period n-i+1
pi = 1/CDF if given CDF
ELR
sum(mk)
Collective LR claims reserve and burning cost
like BF, depends on portfolio claims experience
Advantage of collective LR over BF
different people get same results provided they use same premiums
calc ELR directly from data so no subjectivity
Individual LR claims reserve
like CL, depends on individual latest claims experience
credibile LR claims reserve, GB, and Nehaus (WN)
iterative ultimate and reserve formulas
optimate credibility credibility weight
*weight that minimizes MSE for reserve
*WN tends to result in estimates closest to optimal cred weight
fi and ti
fi=Var(Ui)/Var(UiBC)
ti = [(fi-1)+sqrt((fi+1)(fi-1+2pi))]/2