Fitting of Probability Distribution on the Pre-Monsoon Precipitation of Different Locations in Bangladesh

Abstract

In this study, different probability distributions have been fitted for the data of pre-monsoon precipitation for 17 different locations in Bangladesh over the period 1961–2014. It is found that for the pre-monsoon precipitation, the Gamma is the best-fitted distribution for the locations of Faridpur, Maijdi Court, Khulna, Barisal, Dhaka, Rangamati, Ishurdi, and Rangpur. Furthermore, the Weibull distribution is well fitted for the pre-monsoon precipitations of Chittagong, Comilla, Cox's Bazar, and Jessore. Finally, the normal distribution is more appropriate for Bogra and Sylhet; and the logistic distribution is appropriately fitted for Mymensingh and Satkhira; whereas the lognormal distribution is fitted well for Srimangal among the probability distributions considered in this study. All of the fitted probability distributions have been selected based on the graphical assessment and several goodness-of-fit criteria.

Keywords: Cumulative distribution, Anderson-Darling, AIC, BIC

Cite this Article Md. Habibur Rahman, Farhana Afrin Duty, Md. Asraful Alam. Fitting of Probability Distribution on the Pre-Monsoon Precipitation of Different Locations in Bangladesh. Research & Reviews: Journal of Statistics. 2017; 6(3): 34–47p.