Estimation of COVID-19 Incidence based on PM2.5 in Chiang Mai, Thailand using New Transformed Estimators in the Presence of Missing Observations

The COVID-19 pandemic has damaged and taken human lives and still affects their daily routine and way of living. There is a connection between COVID-19 incidence and fine particulate matter which is a type of air pollution that causes issues to human health, especially in Chiang Mai, Thailand. Daily estimation of the incidence of COVID-19 can assist Thailand in planning to cope with the increasing number of COVID-19 incidents. Unfortunately, some COVID-19 data are missing, and as a result, it may yield inaccurate results for planning policies using missing data. A novel class of estimators engaging transformation to transform an auxiliary variable is suggested under simple random sampling without replacement, whilst assuming the population mean of an auxiliary variable is not available under uniform nonresponse. The new estimators are used to estimate the official cases of COVID-19 per day and the total patients diagnosed with pneumonia and are on high-flow oxygen therapy in Chiang Mai, Thailand using fine particulate matter with a diameter of 2.5 microns concentration as the auxiliary variable. The estimators that were brought forward performed well compared to the existing ones with a reduced bias and mean square error. The best-proposed estimator gave the estimated daily confirmed cases of around 101 cases and the total number of patients diagnosed with pneumonia and are on high-flow oxygen therapy around 16 cases. The highest efficiency is above 500 more percentage relative efficiency in contrast to the mean imputation method. The suggested estimators are more practical to use with real-world data as they do not require the population means associated with the auxiliary variable.