مقارنة بين طريقتي المركبات الرئيسة و المركبات الرئيسة اللبية في معالجة مشكلة التعدد الخطي لبيانات أعداد المصابين بفيروس كورونا المستجد (Corona Virus)‎

Abstract EN

Principal component method is often used to avoid the Multicollinearity problem between independent variables which turned the linearly related variables into independent linear components.

but when the data does not follow a specific distribution, i.

e.

non-parametric data principal component well not be accurate method.

This aim reviews the Principal Component and the Kernel Principal Component when the data is non-parametric and compare the results of the two methods to find out which method is appropriate to processing the problem of Multicollinearity.

A sample was taken from infected People with Coronavirus (covid-19) registered on the website of the Public Health Department of the Iraqi Ministry of Health and for all governorates of Iraq.

The results show that Kernel Principal Component can reduce the dimensions of the data matrix to (14) variables without losing important information, and it was also able to overcome the problem of Multicollinearity.