Estimation of poisson-generalized pareto compound extreme value distribution by probability-weighted moments and empirical analysis

Abstract

This paper puts forward a Poisson-generalized Pareto (Poisson-GP) distribution. This new form of compound extreme value distribution expands the existing application of compound extreme value distribution, and can be applied to predicting financial risk, large insurance settlement and high-grade earthquake, etc. Compared with the maximum likelihood estimation (MLE) and compound moment estimation (CME), probability-weighted moment estimation (PWME) is used to estimate the parameters of the distribution function. The specific formulas are presented. Through Monte Carlo simulation with sample sizes 10, 20, 50, 100, 1 000, it is concluded that PWME is an efficient method and it behaves steadily. The mean square errors (MSE) of estimators by PWME are much smaller than those of estimators by CME, and there is no significant difference between PWME and MLE. Finally, an example of foreign exchange rate is given. For Dollar/Pound exchange rates from 1990-01-02 to 2006-12-29, this paper formulates the distribution function of the largest loss among the investment losses exceeding a certain threshold by Poisson-GP compound extreme value distribution, and obtains predictive values at different confidence levels.

Keywords

Poisson-generalized Pareto compound extreme value distribution / probability-weighted moment estimation / maximum likelihood estimation / compound moment estimation

References

[1] Liu T., Ma F.. Prediction of extreme wave heights and wind velocities[J]. Journal of the Waterway Port Coastal and Ocean Division, ASCE, 1980, 106(4): 469-479.

[2] Langley R. M., El-Shaarawi A. H.. On the calculation of extreme wave heights: A review[J]. Ocean Engineering, 1986, 13(1): 93-118.

[3] Liu Defu. Long term distributions of hurricane characteristics[C]. In: Proceedings of Offshore Technology Conference. Texas, 1982. 305–313.

[4] Liu D., Wang L., Song Y., et al. Multivariate compound extreme value distribution and its application[J]. Journal of Ocean University of China, 2004, 34(5): 893-902.

[5] Rossi F., Fiorentino M., Versace P.. Two-component extreme value distribution for flood frequency analysis[J]. Water Resources Research, 1984, 20(7): 847-856.

[6] Shi D.. Practical Extreme Value Statistic Method[M]. 2006, Tianjin: Tianjin Science and Technology Press.

[7] Jan B., Yuri G., Jozef T.. Statistics of Extremes Theory and Applications[M]. 2004, Chichester: John Wiley & Sons Ltd.

[8] Ye C.. Moment-type estimators of dependence parameter for GBVE distribution[J]. Acta Mathematicae Applicatae Sinica, 2003, 26(1): 62-71.

[9] Wang M., Ye C., Xu D.. Estimation of structural reliability relative to a dependent bivariate Weibull distribution[J]. Chinese Journal of Applied Probability and Statistics, 2006, 22(2): 127-136.

[10] Yan C., Zhang Z.. Parameter estimators in EV models with missing data[J]. Mathematics in Practice and Theory, 2005, 35(12): 116-122.

[11] Landwehr J. M., Matalas J. R., Wallis J. R.. Probability weighted moments compared with some traditional techniques in estimating Gumbel parameters and quantiles[J]. Water Resources Research, 1979, 15(5): 1055-1064.

[12] Luo C., Wang Z.. The estimates of the parameters of Gumbel distribution and their application to the analysis of the water level data[J]. Chinese Journal of Applied Probability and Statistics, 2005, 21(2): 169 175

[13] Foreign Exchange Rates, 1990–2006. [EB/OL]. http://www. federalreserve. Gov / releases / H10/hist /. 2006-12-29.

[14] Malevergne Y., Pisarenko V., Sornette D.. On the power of generalized extreme value (GEV) and generalized Pareto distribution (GPD) estimators for empirical distributions of stock returns[J]. Applied Financial Economics, 2006, 16(3): 271-289.

[15] Lavenda B. H., Cipollone E.. Extreme value statistics and thermodynamics of earthquakes: After shock sequences[J]. Annali di Geofisica, 2000, 43 967-982.