مقارنة مقدرات بيز القياسية لمعلمة توزيع باريتو باستعمال دوال خسارة مختلفة == A Comparison of Standard Bayes Estimators For Parameter of Paretodistribution Using Different Loss Function
Author name:
اخلاص علي حمودي الحديثي
Supervisor name:
صباح هادي عبود الجاسم
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:
07T3395 - p.pdf
Abstract:
في هذا البحث تم دراسة مقدرات بيز القياسية لمعلمة توزيع باريتو لاربعة دوال خسارة هي : 1. دالة الخسارة التربيعية Squared Error Loss Function 2. دالة الخسارة التربيعية المعدلة Modified Squared Error Loss Function 3. دالة الخسارة الاسية الخطية Linerar E | In this research was studied the standard Bayes estimators for parameter of Pareto Distribution for the following four loss function : 1 - Squared Error Loss Function. 2 - Modified Squared Error Loss Function. 3 - Linear Exponential Loss Function. 4 - Modified Exponential Loss Function. In the theoretical part of this research was derived two standard Bayes Estimators for the second and the third function As for the standard Bayes estimators for the first and the fourth function it were available in the research on the subject. In the experimental part in this research A simulation approach By Monte - Carlo method is used to comparisons between preference of the fourth estimators for parameter of Pareto Distribution taking in to consideration the two statistical indicators Mean Squared error (MSE) and Mean Absolute percentage error (MAPE) for different samples sizes and under certain conditions demonstrated preference of standard Bayes estimator for each function of these functions also was the verification of the theoretical part on the research in experimental and under certain condition of two standard Bayes estimators for the squared error loss function and Modified linear exponential loss function
