Evaluation of Approximation of Fisher Information Matrix in Poisson Mixture Model using High Performance Computing

Thumbnail Image

Files

Neerchal_poster_QingJi_hpcf.pdf (690.89 KB)

Links to Files

http://hpcf-files.umbc.edu/research/posters/Neerchal_poster_QingJi_hpcf.pdf

Permanent Link

http://hdl.handle.net/11603/30106

Collections

UMBC Mathematics and Statistics Department
UMBC Faculty Collection
UMBC Student Collection

Author/Creator

Author/Creator ORCID

https://orcid.org/0000-0003-1745-2292
 https://orcid.org/0000-0002-4440-2330

Date

Type of Work

posters
Text

Department

Program

Citation of Original Publication

Rights

This work was written as part of one of the author's official duties as an Employee of the United States Government and is therefore a work of the United States Government. In accordance with 17 U.S.C. 105, no copyright protection is available for such works under U.S. Law.
Public Domain Mark 1.0

Subjects

Abstract

• Fisher information matrix(FIM) is an essential part in the computation of maximum likelihood estimation(MLE) as well as in obtaining their standard errors • Computation of FIM is resource intensive in some widely used models such as mixture distributions • Neerchal and Morel(1993), Raim (2014), and Raim et. al.(2014) have provided approximations to the FIM • In this project, we apply this approximation idea to a mixture of two Poisson distributions • A program in C with MPI is designed to test the performance of our approximation under various selections of parameter values