×

Entropy, a useful concept in risk theory. (English) Zbl 0649.62098

Summary: Exponential bounds for ruin probabilities similar to the Lundberg bound \(e^{-Ru}\) are considered. They are naturally expressed in terms of the entropy function of the claims distribution. Such bounds are useful because they are easy to calculate numerically, and they are sufficiently accurate for practical purposes. A numerical example from life insurance is presented. The entropy estimates have an interesting structure familiar from thermodynamics, and concepts like “temperature” and “equilibrium” turn out to have relevance in risk theory.

MSC:

62P05 Applications of statistics to actuarial sciences and financial mathematics
PDFBibTeX XMLCite
Full Text: DOI

References:

[1] Bühlmann H., Scand. Actuarial J. pp 116– (1984)
[2] Gerber H., An introduction to mathematical risk theory (1979) · Zbl 0431.62066
[3] DOI: 10.1007/BF00575528 · Zbl 0473.60036 · doi:10.1007/BF00575528
[4] Martin-Löf A., Probability and mathematical statistics (1983)
[5] Roberts A. W., Convex functions (1973) · Zbl 0271.26009
This reference list is based on information provided by the publisher or from digital mathematics libraries. Its items are heuristically matched to zbMATH identifiers and may contain data conversion errors. In some cases that data have been complemented/enhanced by data from zbMATH Open. This attempts to reflect the references listed in the original paper as accurately as possible without claiming completeness or a perfect matching.