Skip to content

IAI Actuarial Core Principles · Economic Modelling · Valuing benefit guarantees using simulation

An insurer values a maturity guarantee on a unit-linked policy by Monte Carlo simulation and estimates the guarantee cost as the sample mean of discounted payoffs from n independent simulations. If the insurer wants to halve the standard error of the estimate, holding everything else fixed, how many simulations are needed?

Four times as many simulations are needed. The standard error of a Monte Carlo mean falls in proportion to one over the square root of n, so halving it requires the square root of n to double, which means quadrupling n.

  1. ATwice as many
  2. BFour times as manyCorrect
  3. CEight times as many
  4. DSixteen times as many
  5. The same number, but with a different seed

Explanation

The standard error equals sigma divided by the square root of n. To halve it, the square root of n must double, so n must rise by a factor of four. Doubling n only cuts the standard error by about 29%, so option A is wrong.

Did you get it right without looking?

One question tells you little. A timed set on Valuing benefit guarantees using simulation shows your real accuracy, how long you take and where you lose marks.

Practise Valuing benefit guarantees using simulationFree diagnostic mock

More Valuing benefit guarantees using simulation questions