Sebaran Generalized Extreme Value (GEV) dan Generalized Pareto (GP) untuk Pendugaan Curah Hujan Ekstrim di Wilayah DKI Jakarta

Achi Rinaldi

Abstract


Extreme event such as extreme rainfall have been analyzed and most concern for the country all around the world. There are two common distribution for extreme value which are Generalized Extreme Value distribution and Generalized Pareto distribution. These two distribution have shown good performace to estimate the parameter of  extreme value. This research was aim to estimate parameter of extreme value using GEV distribution and GP distribution, and also to characterized effect of extreme event such as flood. The rainfall data was taken from BMKG for 5 location in DKI Jakarta. Both of distribution shown a good perfromance. The resut showed that Tanjung Priok station has biggest location parameter for GEV and also the biggest scale parameter for GP, that mean the biggest probability to take flood effect of the extreme rainfall.


Keywords


Extreme event; Generalized Extreme Value; Generalized Pareto.

References


Coles, S. (1993). Regional Modelling of Extreme Storms via Max-Stable Processes. Journal of the Royal Statistical Society Series B., 55: 797–816.

Coles, S. (2001). Improving the analysis of extreme wind speeds with information sharing models. Notes de Institut Pierre Simon Laplace, 11: 23-34.

Coles, S., & Tawn, J. (1996). A Bayes analysis of extreme rainfall data. Applied Statistics, 45: 463-478.

Gilli, M., & Këllezi , E. (2006). An Application of Extreme Value Theory for Measuring Financial Risk. Computational Economics, 27: 207-228.

Hosking, J., & Wallis, J. (1987). Parameter and quantile estimation for the generalized . Technometrics, 29: 339-349.

Nelder, J., & Mead, R. (1965. ). A simplex method for function minimization. Computer Journal, 7: 308–313.

Tawn, J. (1988). Bivariate Extreme Value Theory: Models and Estimation. Biometrika, 75:397-415.




DOI: http://dx.doi.org/10.24042/ajpm.v7i1.137

Refbacks

  • There are currently no refbacks.


 

Creative Commons License
Al-Jabar : Jurnal Pendidikan Matematika is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.