Slope estimation in replicated linear functional relationship model via trimmed mean: A simulation study

A nonparametric method using the trimmed mean is proposed to estimate the slope parameter of the replicated linear functional relationship model (LFRM). This study considers the replicated LFRM when the error terms are not assumed to have a normal distribution. The maximum likelihood estimation meth...

Full description

Saved in:
Bibliographic Details
Main Authors: Arif, Azuraini Mohd, Zubairi, Yong Zulina, Hussin, Abdul Ghapor
Format: Conference Proceeding
Language:English
Subjects:
Error analysis
Mathematical models
Maximum likelihood estimation
Normal distribution
Outliers (statistics)
Parameters
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:A nonparametric method using the trimmed mean is proposed to estimate the slope parameter of the replicated linear functional relationship model (LFRM). This study considers the replicated LFRM when the error terms are not assumed to have a normal distribution. The maximum likelihood estimation method requires the assumption of normality and may lead to errors when outliers are present in the data. The performance of the proposed method is compared with the maximum likelihood estimation method in terms of estimated bias and mean square error. Results simulation study highlighted that the proposed method provides a better estimate of the slope parameter in the presence of outliers as compared to the maximum likelihood estimation method.
ISSN:0094-243X
1551-7616
DOI:10.1063/5.0192108