Robust Minium Bias Iteration Algorithms for Classification Ratemaking and Loss Reserving.

Autor: Bae, Taehan
Zdroj: Lobachevskii Journal of Mathematics; Sep2022, Vol. 43 Issue 9, p2387-2396, 10p
Abstrakt: The minimum bias iteration algorithms are commonly used for various applications in non-life insurance and predictive modelling. By applying the robust estimation methods available for generalized linear models, we construct robust versions of minimum bias iteration algorithms. Both multiplicative and additive models are considered for classification ratemaking with an illustration on auto collision data. An application of the multiplicative model to loss reserving renders a robust version of the well known chain-ladder method. [ABSTRACT FROM AUTHOR]
Databáze: Complementary Index