ارسل ملاحظاتك

ارسل ملاحظاتك لنا







Robust Sparse Minimum Average Variance Estimation through Adaptive Elastic Net

المصدر: مجلة القادسية للعلوم الإدارية والاقتصادية
الناشر: جامعة القادسية - كلية الادارة والاقتصاد
المؤلف الرئيسي: Tuama, Sanaa Jabbar (Author)
مؤلفين آخرين: Alkenani, Ali J. Kadhim (Co-Author)
المجلد/العدد: مج25, ع1
محكمة: نعم
الدولة: العراق
التاريخ الميلادي: 2023
الصفحات: 161 - 174
ISSN: 1816-9171
رقم MD: 1367947
نوع المحتوى: بحوث ومقالات
اللغة: الإنجليزية
قواعد المعلومات: EcoLink
مواضيع:
كلمات المؤلف المفتاحية:
Adaptive Elastic Net | Robust Estimation | MAVE | Dimension Reduction
رابط المحتوى:
صورة الغلاف QR قانون
حفظ في:
LEADER 03012nam a22002297a 4500
001 2119669
041 |a eng 
044 |b العراق 
100 |9 725100  |a Tuama, Sanaa Jabbar  |e Author 
245 |a Robust Sparse Minimum Average Variance Estimation through Adaptive Elastic Net 
260 |b جامعة القادسية - كلية الادارة والاقتصاد  |c 2023 
300 |a 161 - 174 
336 |a بحوث ومقالات  |b Article 
520 |b Regression analysis is a difficult method when there are many variables. In other words, as the number of variables increases, the model becomes more complex. This may lead to a dimensional problem. Some explanatory variables do not have a significant effect on the dependent variable, and some of these variables also have an internal correlation with each other, and this requires excluding such variables in order to increase the accuracy of the model. There are two ways to reduce the dimensions, namely the method of selecting variables (v.s) variable selection and variables extractions. Under the assumptions of the theory of SDR (Sufficient dimension reduction), the researchers worked on proposing methods to reduce the dimensions, including the integration of SDR methods with regularization methods (Regularization method) and the methods of regulation mean adding a penalty limit to control the complexity of the model as it greatly reduces the variance of the model, and among these methods SMAVE-AdEN (Alkenani and Rahman, 2020) is a method for selecting a variable under the assumptions of SDR theory. The SMAVE-AdEN method is a combination of Adaptive elastic net with MAVE ( Minimum average variance estimator ) method for estimating minimum average variance. This method is effective when the variables are highly correlated under SDR assumptions. But the SMAVE-AdEN method is not immune and it is a sensitive method that is affected when there are outliers in the data, owing to the least squares criteria that we employ. In this paper, we proposed a robust method (RSMAVE-AdEN), which can estimate parameters and select variables simultaneously, and is not affected by the presence of outliers in explanatory variables and response variables. The effectiveness of the proposed method was verified by a simulation study. 
653 |a الانحدار الذاتي  |a حقوق السحب  |a الشبكات المرنة  |a العمليات الإحصائية 
692 |b Adaptive Elastic Net  |b Robust Estimation  |b MAVE  |b Dimension Reduction 
700 |9 725101  |a Alkenani, Ali J. Kadhim  |e Co-Author 
773 |4 الاقتصاد  |4 إدارة الأعمال  |6 Economics  |6 Business  |c 010  |e Al-Qadisiyah Journal for Administrative & Economic Sciences  |f Maǧallaẗ al-qādisiyyaẗ li-l-ʻulūm al-idāriyyaẗ wa-al-iqtiṣādiyyaẗ  |l 001  |m مج25, ع1  |o 0478  |s مجلة القادسية للعلوم الإدارية والاقتصادية  |v 025  |x 1816-9171 
856 |u 0478-025-001-010.pdf 
930 |d n  |p y  |q n 
995 |a EcoLink 
999 |c 1367947  |d 1367947 

عناصر مشابهة