الفهرس 
Title : Kummaraswamy Regression Models with Application
AbstractOnly 14 pages are availabe for public view
 |  | from | 107 |  |  |
| | | from | 107 | | |
Abstract
Regression analysis is one of the most commonly statistical techniques used for analyzing data in different fields. And used to fit the relation between the dependent variable and the independent variables require strong assumption to be met in the model
Linear models are a way of describing a response variable in terms of a linear combination of predictor variables. The response should be a continuous variable and be at least approximately normally distributed. Such models find wide application but cannot handle clearly discrete or skewed continuous responses. Generalized linear models (GLMs) allow the extension of linear modeling ideas to a wider class of response types, such as count data or binary responses.
Many statistical methods exist for such data types, but the advantage of the GLM approach is that it unites a seemingly disparate collection of response types under a common modeling methodology. Estimation, testing, and diagnostics for this class of models follow a standard path. The ideas behind GLMs were developed over many years by many researchers, so The problem of the current research is to try to provide a new regression for some mathematical distributions to reach solutions to some daily problem
A simulation study was conducted to generate data on the new regression model at different sizes of the sample as well as at different values of parameters. Monte Carlo method was used to generate data and it was done according to some scales where the criteria used for comparison are bias (BAIS)) as well as mean square error (MSE) as well as mean error Absolute (MAE) has been compared between the different sizes of the sample, as well as the different values of the parameters in the
iv light of those measures, and the study concluded that small sizes are better when generating data using the Kumaraswamy model
The study also made a comparison between the Kumaraswamy Lindley regression model, as well as the generalized Lindley regression model and the Lindley regression model in the light of some statistical measures (BIC) Bayesian information criteria and (AIC)) as well as (HQIC), and the study concluded that the Kumaraswamy Lindley regression model is the best from a generalized regression model to Lindley as well as a regression model to Lindley.
The study presented some new mathematical properties of the Kumaraswamy Lindley distribution, and it was one of the most important properties that was studied is to determine the skewness and kurtosis of the proposed distribution, as well as calculating the coefficient of covariance for the new distribution.