DefinePK

Abstract

The generalize distribution from a classical distribution is performed by adding more parameters to the distribution that makes the distribution more flexible in analyzing empirical data and able to adjust the shape of empirical data. The generalization of this distribution produces a Beta Generalized of the first kind distribution or a GB2 distribution with three and four parameters. This paper will discuss the GB2 distribution with four parameters namely a, p and q as shape parameters while parameter b is the scale parameter. In statistical inference, especially parameter estimation, is needed in analyzing empirical data with this distribution. Obviously the estimation results obtained are expected to be a sound estimator, namely to meet the criteria of unbiasedness and minimum variance. The estimation results of the GB2 distribution parameters through simulations using the methods of moment, the Maximum Likelihood Estimation, and the Probability Weighted Moment. Based on the results from the simulation of the three estimation methods that the estimation of parameters by using the Maximum Likelihood Estimation is better than the method of Probability Weighted Moment and the method of moment where in a larger sample size gives a smaller bias and MSE value.