Mokhtar, Siti Fairus and Md Yusof, Zahayu and Sapiri, Hasimah Confidence Interval Estimation Using Bootstrapping Methods And Maximum Likelihood Estimate. In: The 5 International Conference on Computing, Mathematics and Statistics 2021 (iCMS2021), 4 - 5 August 2021, Universiti Teknologi MARA (UiTM) Kedah, Malaysia.

PDF - Published Version Restricted to Registered users only Download (954kB) | Request a copy

Abstract

Confidence interval estimation is an important technique to estimate parameter of a population calculated from a sample drawn from the population. The objective of this study is to present the steps to calculate confidence interval using SPSS. The objective of this paper also is to compare confidence interval using maximum likelihood estimate, percentile bootstrap, and bias-corrected and accelerated methods.Bootstrap is not commonly used because this method is complex to calculate. The advantages of bootstrapping are valid for small samples, and it is a convenient tool. The study found that the BCa method produced CIs closer to the desired level of the coverage than the other methods.

Item Type:	Conference or Workshop Item (Paper)
Additional Information:	e-ISBN: 978-967-2948-12-4
Uncontrolled Keywords:	Bootstrapping method, confidence interval, maximum likelihood estimate
Subjects:	T Technology > T Technology (General)
Divisions:	School of Quantitative Sciences
Depositing User:	Mdm. Sarkina Mat Saad @ Shaari
Date Deposited:	30 Apr 2024 13:09
Last Modified:	30 Apr 2024 13:09
URI:	https://repo.uum.edu.my/id/eprint/30763

Actions (login required)

View Item