Comparison of weighted estimated method and proposed method (BEMW) for estimation of semi-parametric model under incomplete data

Authors

  • سعد كاظم حمزة
  • رند هيثم عبد الحسين

DOI:

https://doi.org/10.33095/jeas.v26i120.1923

Keywords:

partial linear regression, Nadarya-Watson, Weighted estimators, suggest method (Expectation-Maximization with Bootstrapping Weighted) (EMBW), الانحدار الخطي الجزئي , نداريا واتسون, المقدرات الموزونة, الطريقة المقترحة

Abstract

Generally, statistical methods are used in various fields of science, especially in the research field, in which Statistical analysis is carried out by adopting several techniques, according to the nature of the study and its objectives. One of these techniques is building statistical models, which is done through regression models. This technique is considered one of the most important statistical methods for studying the relationship between a dependent variable, also called (the response variable) and the other variables, called covariate variables. This research describes the estimation of the partial linear regression model, as well as the estimation of the “missing at random” values (MAR). Regarding the parametric part, a method has been developed to estimate the parametric of the partial linear regression model represented by weighted estimators as well as by the suggested method (EMBW). Two methods of the simulation were compared using three sizes (n = 100,150,200) and using three different values for and zero mean and it was found that the proposed method (EMBW) was superior to the weighted estimator method.

Downloads

Download data is not yet available.

Published

2020-06-30

Issue

Section

Statistical Researches

How to Cite

“Comparison of weighted estimated method and proposed method (BEMW) for estimation of semi-parametric model under incomplete data” (2020) Journal of Economics and Administrative Sciences, 26(120), pp. 395–410. doi:10.33095/jeas.v26i120.1923.

Similar Articles

1-10 of 862

You may also start an advanced similarity search for this article.