A Geometric Approach to Confidence Sets for Ratios: Fieller‘s Theorem, Generalizations, and Bootstrap

We present a geometric method to determine confidence sets for the ratio E(Y )/E(X) of the means of random variables X and Y. This method reduces the problem of constructing confidence sets for the ratio of two random variables to the problem of constructing confidence sets for the means of one-dimensional random variables. It is valid in a large variety of circumstances. In the case of normally distributed random variables, the so-constructed confidence sets coincide with the standard Fieller confidence sets. Generalizations of our construction lead to definitions of exact and conservative confidence sets for very general classes of distributions, provided the joint expectation of (X, Y ) exists and linear combina- tions of the form aX + bY are well-behaved. Finally, our geometric method allows us to derive a very simple bootstrap approach for constructing conservative confi- dence sets for ratios that perform favorably in certain situations, in particular in the asymmetric heavy-tailed regime.