Özet:

In this article we introduce and study a new four-parameter distribution, called odd generalized exponential power function distribution based on the odd generalized exponential generated family. The proposed model serves as an extension of the two-parameter power distribution as well as includes the odds exponential power function distribution as a new sub-model. Expressions for the moments, probability weigthed moments, quantile function, Bonferroni and Lorenz curves, Rényi entropy and order statistics are obtained. The model parameters are estimated based on the maximum likelihood and percentile methods of estimation. A simulation study is carried out to evaluate and compare the performance of different estimators in terms of their biases, standard errors and mean square errors. Eventually, the practical importance and flexibility of the proposed distribution in modelling real data application is examined.  It has been concluded that the new distribution works better than some other extensions of the power function distribution.

Anahtar Kelimeler: