Hi,
I'd appreciate any thoughts/references to solve the following problem.
I need to determine the expected insurance cost (i.e, pure premium) for each
vehicle on an hypothetical insurance portfolio. Each vehicle i={1,.....,m}
is driven by n_i drivers (so the number of drivers can vary by vehicle). I
have rating factors and insurance loss data at the driver level, so I can
first determine the expected insurance cost at the driver level and then
aggregate the cost at the vehicle level. The question is what would be a
reasonable way to aggregate that data at the vehicle level. Since I don't
know the proportion of time that each driver is on the vehicle, what would
be a reasonable way to allocate exposure time to each driver?
Any reference paper or ideas would be highly appreciated!
Thanks,
Lars.
You may leave the list at any time by sending the command
SIGNOFF allstat
to [log in to unmask], leaving the subject line blank.
|