Comparing two means in count models having random effects - a UMPU test

Yasuhiro Omori ()

Statistics & Probability Letters, 1997, vol. 34, issue 3, 225-235

Abstract: We propose a model for bivariate count data that includes a common random effect; conditional on the random effects; the marginal distributions consist of independent Poisson distributions. Uniformly, most powerful tests are derived for comparing the unconditional means of the two component count distributions for a variety of random effects distributions. The optimal test turns out to be the standard binomial test obtained by conditioning on the total number of events from both components. A numerical calculation is performed to compare the power of the proposed test with the likelihood test under various conditions.

Keywords: Uniformly; most; powerful; test; Random; effect; Likelihood; ratio; test (search for similar items in EconPapers)
Date: 1997
References: View complete reference list from CitEc
Citations:

Downloads: (external link)
http://www.sciencedirect.com/science/article/pii/S0167-7152(96)00185-X
Full text for ScienceDirect subscribers only

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:eee:stapro:v:34:y:1997:i:3:p:225-235

Ordering information: This journal article can be ordered from
http://www.elsevier.com/wps/find/supportfaq.cws_home/regional
https://shop.elsevie ... _01_ooc_1&version=01

Access Statistics for this article

Statistics & Probability Letters is currently edited by Somnath Datta and Hira L. Koul

More articles in Statistics & Probability Letters from Elsevier
Bibliographic data for series maintained by Catherine Liu ().