A Characterization of Convoluted Geometric Distributions.
Abstract
Let X be a nonnegative integer-valued random variable whose distribution is that of the sum of geometric variable Y with parameter theta and a nonnegative integer-valued random variable Z independent of Y whose distribution does not depend on theta. The class of all such distributions are characterized by a system of differential equations satisfied by their probability mass functions. The characterization is shown to be useful in maximum likelihood estimation of the parameter theta when the distribution of Z is known.
Document Details
- Document Type
- Technical Report
- Publication Date
- May 01, 1977
- Accession Number
- ADA042136
Entities
People
- Francisco J. Samaniego
Organizations
- University of California, Davis