Share
مقارنة بعض الطرق الحصينة للمربعات الصغرى الجزئية == Compare Some of Robust Methods For Partial Least Squares
Author name:
ميسون علي رحمن المندلاوي
Supervisor name:
هلال عبود البياتي
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:
07T4096 - p.pdf
Abstract:
الحمد لله والصلاة والسلام على رسول الله سيدنا محمد (صلى الله عليه وسلم )وعلى اله وصحبه وسلم اما بعد...يتناول البحث استخدام انحدار المربعات الصغرى الجزئية PLS)) Partial Least Squares وهي تقنية انحدار خطي طورت للتعامل مع انحدارات ذات ابعاد عالية لمتغير وا | Partial least squares regression ( PLRS) is a linear regression technique developed to deal with high - dimensional regression and one or several response variables. In this paper we introduce robustified version of the SIMPLS algorithm being the leading PLRS algorithm because of its speed and efficiency. Because SIMPLS is based on the empirical cross - covariance matrix between the response variables and the regressors and on linear least squares regression, the results are affected by abnormal observations in the data set. Two robust methods covariance matrix for high - dimensional data and robust linear regression. We introduce robust RMSECV and RMSEP values for model calibration and model validation diagnostic plots are constructed to visualize and classify the outliers. Several simulation results and the analysis of real data sets show the effectiveness and the robustness of the approaches. Because RSIMPLS is roughly twice as fast as RSIMCD, it stands out as the overall best method.
