Generalized inference for the common mean of several lognormal populations

Abstract

A hypothesis testing and an interval estimation are studied for the common mean of several lognormal populations. Two methods are given based on the concept of generalized p-value and generalized confidence interval. These new methods are exact and can be used without restriction on sample sizes, number of populations, or difference hypotheses. A simulation study for coverage probability, size and power shown that the new methods are better than the existing methods. A numerical example is given with some real medical data.