Robust Ratio Estimation with an Application to Covid-19 Data from Louisiana

Traditional ratio estimator loses its efficiency when there are outliers in the data or when the error term is not normally distributed. Specifically in health-related data, many biological processes can be modeled by Laplace distribution. We propose a novel robust ratio estimator that utilizes Lloyd’s estimator for the cases where the error term is from the Laplace distribution. We derive the mean square error of the proposed estimator and compare it with some other existing estimators using extensive simulations. We use the proposed estimator to estimate Covid-19 cases and deaths in Louisiana and demonstrate its performance.