Detection and correction of outliers in the bivariate chainladder method
Faculty of Sciences. Mathematics and Computer Science
Insurance: mathematics and economics. - Amsterdam
, p. 188-193
University of Antwerp
The expected profit or loss of a non-life insurance company is determined for the whole of its multiple business lines. This implies the study of the claims reserving problem for a portfolio consisting of several correlated run-off triangles. A popular technique to deal with such a portfolio is the multivariate chainladder method of Merz and Wüthrich (2008). However, it is well known that the chainladder method is very sensitive to outlying data. For the univariate case, we have already developed a robust version of the chainladder method. In this article we propose two techniques to detect and correct outlying values in a bivariate situation. The methodologies are illustrated and compared on real examples from practice.