FORECASTING OF CLAIM BY COMBINING PROBABILITY DISTRIBUTIONS

Abstract

Purpose- The purpose of this study is to focus on forecasting the total claim distribution of fire-disaster and transportation insurances by combining probabilities of claim distribution using the data for 2014 and 2015.

Methodology- In this study, the combination of Weibull and Gamma distributions of fire-disaster and transport policies are discussed. By combining two different probability density function (PDF), a single PDF is derived and thus it is aimed to provide convenience in calculations.

Findings- Two probability distributions were combined with mathematical methods. As a result, a single probability density function was obtained. This probability density function can represent the total claim distribution.

Conclusion- In conclusion, we used the data regarding fire-disaster and transportation insurances for 2014 and 2015. Insurance firms that offer these two policies to their customers need to determine their risk taking into consideration the total claim distribution from the policies. Since Weibull and Gamma distributions have a PDF, it is necessary to integrate the multiplication of the characteristic functions for combining these two distributions. The PDF obtained as a result of mathematical operations is the PDF of the total claim distribution.

Keywords

• Claim distributions,combining probability distributions,insurance,total claim distribution,actuarial models.

References

1. Armutlu, İ. H. (1999). İşletme istatistiğine giriş. Beta Basım Yayım Dağıtım.
2. Benckert, L. G., Jung, J. (1974). Statistical models of claim distributions in fire insurance. ASTIN Bulletin: The Journal of the IAA, 8(1), 1-25.
3. Clemen, R. T., Winkler, R. L. (1999). Combining probability distributions from experts in risk analysis. Risk analysis, 19(2), 187-203.
4. Çekici, M. E., İnel, M. N. (2013). Türk sigorta sektörünün direkt prim üretimlerinin tahmin teknikleri ile incelenmesi. Marmara Üniversitesi İ.İ.B. Dergisi, 34(1), 135-152.
5. Eısekberg, E., Gale, D. (1959). Consensus of subjective probabilities: the pari-mutuel method. Ann. Math. Statist. Vol. 30 (1959), pp. 165-168.
6. Genest, C., Zidek, J. V. (1986). Combining probability distributions: a critique and an annotated bibliography. Statistical Science, 1(1), 114-135.
7. Hill, T. P., Miller, J. (2011). How to combine independent data sets for the same quantity. Chaos: An Interdisciplinary Journal of Nonlinear Science, 21.3 (2011): 033102-1.
8. Hill, T. (2011). Conflations of probability distributions. Transactions of the American Mathematical Society 363.6 (2011): 3351-3372.

9. Liu, X., Ghorpade, A., Tu, Y. L., Zhang, W. J. (2012). A novel approach to probability distribution aggregation. Information Sciences, 188 (2012), 269-275.
10. McMillan, R. W., Barnes, N. P. (1976). Detection of optical pulses: the effect of atmospheric scintillation. Applied Optics, Vol. 15, No. 10, Ekim 1976.
11. McMillan, R. W., Kohlberg, I. (2017). A simple method for combining probability distribution functions relevant to radar and communications systems. IEEE International Conference on Microwaves, Antennas, Communications and Electronic Systems (COMCAS), (2017).
12. Morrıs, P. A. (1974). Decision analysis expert use. Management Sci., Vol. 20 (1974), pp. 1233-1241.
13. Pırıldak, M., Esensoy, Ö. Bağımli riskler için toplam hasar miktarinin dağilimi. İstatistikçiler Dergisi: İstatistik ve Aktüerya, 1(1), 68-79.
14. Roberts, H. V. (1965). Probabilistic prediction. J. Amer. Statist. Assoc., Vol. 60 (1965), pp. 50-62.
15. Stone, M. (1961). The opinion pool. Ann. Math. Statist., Vol. 32 (1961), 1339-1342.
16. Tse, Y. K. (2009). Nonlife actuarial models: theory, methods and evaluation. Cambridge University Press.
17. Winkler, R. L. (1968). The consensus of subjective probability distributions. Management Sci., Vol. 15 (1968), pp. B61-B75. www.hazine.gov.tr