Directed likelihood ratio tests for ordered alternatives and inference results for the star-shaped restriction

Arthur Cohen, Harold Sackrowitz

Research output: Contribution to journalArticle

1 Citation (Scopus)

Abstract

To test a null hypothesis of homogeneity of parameters versus an order restricted alternative a popular method is to use a restricted likelihood ratio test. An alternative approach which oftentimes has desirable properties is a directed likelihood ratio test. In this paper, we give sufficient conditions under which these approaches coincide. We indicate cases where they do not coincide. One such case is where the parameters satisfy the lower star-shaped restriction and the underlying random variables are independent with Poisson distributions. For this model, we study and prefer the directed likelihood ratio test. We also propose estimators of the parameters which we feel are more desirable than the maximum likelihood estimators.

Original languageEnglish (US)
Pages (from-to)181-189
Number of pages9
JournalJournal of Statistical Planning and Inference
Volume103
Issue number1-2
DOIs
StatePublished - Apr 15 2002

Fingerprint

Ordered Alternatives
Poisson distribution
Likelihood Ratio Test
Random variables
Maximum likelihood
Stars
Star
Restriction
Alternatives
Null hypothesis
Homogeneity
Maximum Likelihood Estimator
Random variable
Estimator
Sufficient Conditions
Likelihood ratio test
Inference
Model

All Science Journal Classification (ASJC) codes

  • Statistics and Probability
  • Statistics, Probability and Uncertainty
  • Applied Mathematics

Keywords

  • Cone order monotonicity
  • Maximum likelihood estimators
  • Order restricted inference
  • Preservation of order
  • Projections

Cite this

@article{c0f162d0e5b04a73b46d4bfe270241ca,
title = "Directed likelihood ratio tests for ordered alternatives and inference results for the star-shaped restriction",
abstract = "To test a null hypothesis of homogeneity of parameters versus an order restricted alternative a popular method is to use a restricted likelihood ratio test. An alternative approach which oftentimes has desirable properties is a directed likelihood ratio test. In this paper, we give sufficient conditions under which these approaches coincide. We indicate cases where they do not coincide. One such case is where the parameters satisfy the lower star-shaped restriction and the underlying random variables are independent with Poisson distributions. For this model, we study and prefer the directed likelihood ratio test. We also propose estimators of the parameters which we feel are more desirable than the maximum likelihood estimators.",
keywords = "Cone order monotonicity, Maximum likelihood estimators, Order restricted inference, Preservation of order, Projections",
author = "Arthur Cohen and Harold Sackrowitz",
year = "2002",
month = "4",
day = "15",
doi = "10.1016/S0378-3758(01)00220-8",
language = "English (US)",
volume = "103",
pages = "181--189",
journal = "Journal of Statistical Planning and Inference",
issn = "0378-3758",
publisher = "Elsevier",
number = "1-2",

}

Directed likelihood ratio tests for ordered alternatives and inference results for the star-shaped restriction. / Cohen, Arthur; Sackrowitz, Harold.

In: Journal of Statistical Planning and Inference, Vol. 103, No. 1-2, 15.04.2002, p. 181-189.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Directed likelihood ratio tests for ordered alternatives and inference results for the star-shaped restriction

AU - Cohen, Arthur

AU - Sackrowitz, Harold

PY - 2002/4/15

Y1 - 2002/4/15

N2 - To test a null hypothesis of homogeneity of parameters versus an order restricted alternative a popular method is to use a restricted likelihood ratio test. An alternative approach which oftentimes has desirable properties is a directed likelihood ratio test. In this paper, we give sufficient conditions under which these approaches coincide. We indicate cases where they do not coincide. One such case is where the parameters satisfy the lower star-shaped restriction and the underlying random variables are independent with Poisson distributions. For this model, we study and prefer the directed likelihood ratio test. We also propose estimators of the parameters which we feel are more desirable than the maximum likelihood estimators.

AB - To test a null hypothesis of homogeneity of parameters versus an order restricted alternative a popular method is to use a restricted likelihood ratio test. An alternative approach which oftentimes has desirable properties is a directed likelihood ratio test. In this paper, we give sufficient conditions under which these approaches coincide. We indicate cases where they do not coincide. One such case is where the parameters satisfy the lower star-shaped restriction and the underlying random variables are independent with Poisson distributions. For this model, we study and prefer the directed likelihood ratio test. We also propose estimators of the parameters which we feel are more desirable than the maximum likelihood estimators.

KW - Cone order monotonicity

KW - Maximum likelihood estimators

KW - Order restricted inference

KW - Preservation of order

KW - Projections

UR - http://www.scopus.com/inward/record.url?scp=0037089891&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0037089891&partnerID=8YFLogxK

U2 - 10.1016/S0378-3758(01)00220-8

DO - 10.1016/S0378-3758(01)00220-8

M3 - Article

AN - SCOPUS:0037089891

VL - 103

SP - 181

EP - 189

JO - Journal of Statistical Planning and Inference

JF - Journal of Statistical Planning and Inference

SN - 0378-3758

IS - 1-2

ER -