![]() | Only 14 pages are availabe for public view |
Abstract Statistical models may be used to describe and predict real-world events. Over the last few decades, expanded distributions have been widely utilized to represent data in a variety of fields. Recent research has focused on creating new families that expand well-known distributions while still allowing for a significant deal of flexibility in data modeling in practice. The purpose of this thesis is to introduce and investigate two newly produced distribution families, namely the new T-X family and Kumaraswamy odd Fréchet - generated. In the first family, we employed a novel transformation instead of the one used by Alzeatrah et al. (2013), and the Kumaraswamy Fréchet distribution was used as a generator in the second family. In the Kumaraswamy Fréchet - generated family, the odds ratio is used as a transformation. Some statistical characteristics are obtained for each family, and ML estimators are investigated. Each family’s sub models are investigated. In each family, a simulation study is carried out for a certain distribution. Each family’s significance and adaptability are evaluated by applying it to real-world data sets and comparing it to other known distributions |