On a Correlation Inequality and Its Applications
Abstract
This document considers a continuous distribution on (0, infinity) with cdf F, survival function F (overlined) = 1-F and cumulative hazard function H = LnF(overlined). For F NBUE it is shown that the correlation coefficient between X approx. = F and H(X) is bounded below by delta/mu, the coefficient of variation of F, while for F NWUE the correlation coefficient is bounded below by mu/delta. Several applications of this inequality and its generalizations are discussed, including Monte-Carlo simulation of the renewal function, exponential approximation of DMRL distributions, moment inequalities for record values and a variance inequality for random event epochs in a homogeneous Poisson process.
Document Details
- Document Type
- Technical Report
- Publication Date
- Mar 29, 1988
- Accession Number
- ADA198295
Entities
People
- Mark O. Brown
Organizations
- City College of New York