تقديرات معلمات انموذج الانحدار متعدد العوامل - متعدد الحدود من الدرجة الثانية مع تطبيق عملي == Estimations Parameters Multi - Factor - A Polynomial of The Second Degree Regression With Practical Application
Author name:
غيث عبد الشهيد كاظم السلطاني
Supervisor name:
احمد ذياب احمد العزاوي
General topic:
Administration and Economics
Specific topic:
Statistics
Degree:
Master
University:
University of Baghdad - Faculty Of Administration And Economics - Department Of Statistics
Language:
Arabic
University location:
Baghdad
First pages:
07T3931 - p.pdf
Abstract:
في انماذج الانحدار تكون عادة العلاقة بين المتغير المعتمد ( ) والمتغير المستقل ( ) او المتغيرات المستقلة ( ) خطية وفي انماذج اخرى تكون لا خطية. وان انموذج الانحدار المتعدد العوامل - المتعدد الحدود من الدرجة الثانية من النماذج اللاخطية والتي يمكن من خلاله ا | Regression models for the relationship between the dependent variable (Y) and the independent variable (X) or independent variables (X’s) which are linear or nonlinear. And multiple regression model factors - Multi - border second class of nonlinear models that can get through the estimators of its parameters. In our research was one of the hypotheses regression unrealized, which is that the random error distribution was the distribution of non - identical (Generalized logistic distribution) which led to the use of more accurate methods than the ordinary methods , such as method of robust Laplace and modified maximum likelihood to obtain a estimates of multiple regression parameters factors - multiple modalities border from the second division. On the theoretical side of this research it was addressed to display some specimen multi - factor regression parameters estimates formats - Multi - border quadratic using ordinary least squares method and the method of the modified maximum likelihood and robust Laplace. In the Experimental side it has been the work of experiments using simulation and comparison of these experiments was the use of the index statistical mean square error of the parameters for the model, and through comparison between the methods show that the modified maximum likelihood was the best. As the best values for my shape parameter and scale parameter (b=1,?=1 ) and each sample sizes (n = 20,50.100). As it has been the application of the modified maximum likelihood to real data represent the fact that your natural hormone insulin diabetes depending on the enzyme GOT data, and the GPT enzyme and hormone Hbalc.It was reached to increase the hormone Hbalc lead to a decrease in the hormone's natural insulin diabetes and this leads to an increase in blood sugar, and increase the enzyme GOT and GPT enzyme leads to increased natural hormone insulin.
