Scholarlink

<p>In the regression analysis, ordinary least squares techniques are commonly used. However, the data’s outcomes will be untrustworthy if there is an outlier in them. In order to deal with the outlier problem, various robust regression methods such as LTS, LMS, LAD, Huber-M, Hample-M, Tukey-M, and Huber-MM have been frequently presented as alternatives to OLS for a long time. In this article, primarily modified exponential ratio-type estimators based on OLS techniques are suggested. After that, robust regression method estimators are proposed, which is a useful strategy. The application of robust regression methods enhanced the efficiency of the estimators, especially for outliers in the data. The MSE equations of the various estimators are computed and compared to OLS approaches. Numerical illustration and simulation studies are performed on R program software to support our theoretical findings.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Assessing the Performance of Regression-Based Exponential Estimators in the Presence of Outliers: A Simulation Study

  • 期刊论文

  • 发表日期：

    2025年11月22日

查看全文
  • Vinay Kumar Yadav,
  • Shakti Prasad

摘要

In the regression analysis, ordinary least squares techniques are commonly used. However, the data’s outcomes will be untrustworthy if there is an outlier in them. In order to deal with the outlier problem, various robust regression methods such as LTS, LMS, LAD, Huber-M, Hample-M, Tukey-M, and Huber-MM have been frequently presented as alternatives to OLS for a long time. In this article, primarily modified exponential ratio-type estimators based on OLS techniques are suggested. After that, robust regression method estimators are proposed, which is a useful strategy. The application of robust regression methods enhanced the efficiency of the estimators, especially for outliers in the data. The MSE equations of the various estimators are computed and compared to OLS approaches. Numerical illustration and simulation studies are performed on R program software to support our theoretical findings.