Credibility for Hiawatha

This paper is called credibility for Hiawatha because it is about expected value ratemaking. Like Hiawatha. and unlike users of "classical" credibility. we are concerned today with making good estimates, that is, minimum variance unbiased estimates of the expected value of the outcome of a stochastic process. Our first point is that Bayesian credibility is always better than classical credibility if the goal is to estimate future loss costs. Nonetheless, like Hiawatha, we must consider that: "... an increased precision / Might perhaps be rather better / Even at the risk of bias / If thereby one, now and then, could / Register upon the target." Our second point is that there are tricks you can use to make Bayesian credibility computations easily. Each trick introduces a little bias. but the tricks improve the precision of your estimates as well as making them easy to calculate.