Combining measurements

Abstract

The problem of combining two or more measurements of the same unknown quantity θ can be addressed in general by building a likelihood function that combines two or more data samples. If the measurements are independent, the combined likelihood function is given by the product of the individual likelihood functions and depends on the unknown parameter present in each of them, at least some of which are in common among different measurements. The minimization of the combined likelihood function provides an estimate of θ that takes into account all the individual data samples.