Abstract
We focus on the normal approximation for point estimation of the ratios of medians of two independent, log-normal distributions. We investigate its performance in terms of bias, variance, and mean square error, using Monte Carlo simulations. The results show that the normal approximation, which is relatively simple, provides a reliable result. The normal approximation approaches could be recommended on the basis of the specific values of the parameters and/or sample sizes. The point estimation is illustrated using real data examples.

This publication has 23 references indexed in Scilit: