Confidence disc and square for Cauchy distributions

Abstract

We will construct a confidence region of parameters for a sample of size $N$ from Cauchy distributed random variables. Although Cauchy distribution has two parameters, a location parameter $\mu \in \mathbb{R}$ and a scale parameter $\sigma > 0$, we will infer them at once by regarding them as a single complex parameter $\gamma := \mu + i\sigma$. The region should be a domain in the complex plane, and we will give a simple and concrete formula to give the region as a disc and a square.