Which Stochastic Model is Underlying the Chain Ladder Method?

The usual chain ladder method is a deterministic claims reserving method. In the last years, a stochastic loglinear approximation to the chain ladder method has been used by several authors especially in order to quantify the variability of the estimated claims reserves. Although the reserves estimated by both methods are clearly different, the loglinear approximation as been called `chain ladder', too, by these authors. In this note, we show that a different distribution-free stochastic model is underlying the chain ladder method, i.e. yields exactly the same claims reserves as the usual chain ladder method. Moreover, a comparison of this stochastic model with the above mentioned loglinear approximation reveals that the two models rely on different philosophies of the claims process. Because of these fundamental differences the loglinear approximation deviates from the usual chain ladder method in a decisive way and should therefore not be called `chain ladder' any more. Finally, in the appendix it is shown that the loglinear approximation is much more volatile than the usual chain ladder method.