A Class of Transformed Population Mean Estimators with an Application to Missing COVID-19 Data in Chiang Mai, Thailand

In this paper, a class of population mean estimators is suggested in the presence of missing data in a study variable by transforming an auxiliary variable under simple random sampling without replacement, assuming the population mean of the auxiliary variable is unknown. The unprecedented, detrimental damage caused by the COVID-19 pandemic has afflicted citizens all over the world immensely through the economy, their professions, and personal lives. Global healthcare goals have been impeded due to the sudden impact of the repercussions of the pandemic and healthcare for all has been more difficult to seek than ever. Sometimes the COVID-19 data are missing due to not being recorded and as a result, leads to inefficient interpretation in further analysis based on these data. The properties of the bias and mean square error of the suggested estimators are investigated and the performance shown through an application to COVID-19 data in Chiang Mai, Thailand. The results illustrate that the new class of estimators outperform other estimators giving the smallest bias and mean square error. The suggested estimators give the closest estimated number of COVID-19 patients who have pneumonia and require high-flow oxygen using fine particulate matter.