Efficient imputation methods in case of measurement errors

Anoop Kumar; Shashi Bhushan; Shivam Shukla; M E Bakr; Arwa M Alshangiti; Oluwafemi Samson Balogun

doi:10.1016/j.heliyon.2024.e26864

Efficient imputation methods in case of measurement errors

Heliyon. 2024 Feb 28;10(6):e26864. doi: 10.1016/j.heliyon.2024.e26864. eCollection 2024 Mar 30.

Authors

Anoop Kumar¹, Shashi Bhushan², Shivam Shukla³, M E Bakr⁴, Arwa M Alshangiti⁴, Oluwafemi Samson Balogun⁵

Affiliations

¹ Department of Statistics, Central University of Haryana, Mahendergarh, 123031, India.
² Department of Statistics, University of Lucknow, Lucknow, 226007, India.
³ Department of Statistics, Amity University Uttar Pradesh, Lucknow, 226028, India.
⁴ Department of Statistics and Operations Research, College of Science, King Saud University, P.O. Box 2455, Riyadh 11451, Saudi Arabia.
⁵ Department of Computing, Faculty of Science, Forestry and Technology, University of Eastern Finland, FI-70211, Finland.

Abstract

This manuscript develops few efficient difference and ratio kinds of imputations to handle the situation of missing observations given that these observations are polluted by the measurement errors (ME). The mean square errors of the developed imputations are studied to the primary degree approximation by adopting Taylor series expansion. The proposed imputations are equated with the latest existing imputations presented in the literature. The execution of the proposed imputations is assessed by utilizing a broad empirical study utilizing some real and hypothetically created populations. Appropriate remarks are made for sampling respondents regarding practical applications.

Keywords: 62D05; 62D10; Difference and ratio estimators; Imputation; Measurement errors; Missing data.