Normal functions of normal random variables
It is the purpose of this paper to show that, when X and Y are independent normal random variables with zero means and (possibly unequal) standard deviations \(\sigma\) and \(\tau\), respectively, then \[ Z=(\sigma^{-1}+\tau^{-1})XY/(X^ 2+Y^ 2)^{1/2}\quad and \] \[ W=sign(X)\cdot (\sigma^{-1}X^ 2-\tau^{-1}Y^ 2)/(X^ 2+Y^ 2)^{1/2} \] are independent normal variables, both with mean 0 and variance 1. The parts of this result which exist in the literature have proofs which are needlessly sophisticated and technical. We make use of a simple univariate transformation of a uniform variable.
- Some elementary proofs of the normality of \(XY/(X^ 2+Y^ 2)^{1/2}\) when X and Y are normal
- A result of Shepp
- NORMAL FUNCTIONS WITH BOUNDED COEFFICIENTS
- Why Is the Sum of Independent Normal Random Variables Normal?
- scientific article; zbMATH DE number 853721 (Why is no real title available?)
- Wald tests of singular hypotheses
This page was built for publication: Normal functions of normal random variables
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q1096956)
