تحليل الانحدار المتعدد اللامعلمي مع دالتي Epanechnikov and Gaussion

Abstract EN

The regression analysis is a statistical tool through which we build statistical models in order to estimate the relationship between the dependant variable and the explanatory variables.

Which produce a statistical equation that shows the relationship between these variables This relationship can be used for estimation and prediction.

In most studies, the subject of non-parametric has a clear interest in a more advanced process of statistical analysis aimed at obtaining high-quality competencies.

The simulation method was used to compare the non-parametric model with different size samples and variances using some comparison criterion The aim of this study is to estimate the function of the regression of the non-parametric using the estimatores of (Nadaraya-Watson) & Regression local polynomial) in the case of( Epanechnikov), (Gaussion)) The simulation results was found that the Epaneknikov function is the best when using the estimated Nadaraya-Watson