Actuarial reserve analyses typically rely on a number of different estimation methods to develop indicated ultimate loss. The paid and incurred (i.e., paid plus case) chain ladder methods are the most common, but there are many other actuarial reserving methods. Most of these methods have both paid and incurred versions, and many have several other variations as well.
The various methods diverge significantly, and actuarial judgment is used in selecting ultimate loss. A need exists for empirical evidence to support the use of particular methods over others. This paper analyzes 30 actuarial receiving methods and discusses the effect of correlation between methods on the results and the practical implications of this correlation.
This article was originally published by the CAS in its 2012 Summer Forum Program.