Exact Distribution for the Product of Two Correlated Gaussian Random Variables

This letter considers the distribution of product for two correlated real Gaussian random variables with nonzero means and arbitrary variances, which arises widely in radar and communication societies. We determine the exact probability density function (PDF) in terms of an infinite sum of modified...

Full description

Saved in:
Bibliographic Details
Published inIEEE signal processing letters Vol. 23; no. 11; pp. 1662 - 1666
Main Authors Guolong Cui, Xianxiang Yu, Iommelli, Salvatore, Lingjiang Kong
Format Journal Article
LanguageEnglish
Published IEEE 01.11.2016
Subjects
Approximation error
Convergence
Distribution
exact probability density function (PDF)
Monte Carlo methods
nonzero means and arbitrary variances
Probability density function
Radar
Radar signal processing
Random variables
two correlated real Gaussian random variables
Online AccessGet full text

Cover

More Information
Summary:This letter considers the distribution of product for two correlated real Gaussian random variables with nonzero means and arbitrary variances, which arises widely in radar and communication societies. We determine the exact probability density function (PDF) in terms of an infinite sum of modified Bessel functions of second kind, which includes some existent results, i.e., zero-means and/or independent variables, as special cases. Then, we study the approximation error and convergence rate when finite summations are exploited in practice. Finally, we evaluate the PDF behaviors of the derived expression as well as the Monte Carlo simulations.
ISSN:1070-9908
1558-2361
DOI:10.1109/LSP.2016.2614539