On the use of the quasi-likelihood method in teratological experiments

K. Y. Liang, J. Hanfell

Research output: Contribution to journalArticle

Abstract

This paper concerns the impact of litter effects on the inference of dose- response relationships in teratological experiments with binary response. Kupper et al. (1986, Biometrics 42, 85-98) concluded that when intra-litter correlations are dose-dependent, the use of a common intra-litter correlation likelihood based on the beta-binomial distribution could lead to severe bias in estimation of the parameter β, which characterizes the dose-response relationship. We show here that the problems of bias and coverage probability for β could still be substantial when one uses the likelihood with heterogeneous intra-litter correlations. We then examine through a simulation study the performance of the quasi-likelihood method (Wedderburn, 1974, Biometrika 61, 439-447) and recommend that this method with a common intra- litter correlation parameter be used when the number of litters is small or modest.

Original languageEnglish (US)
Pages (from-to)872-880
Number of pages9
JournalBiometrics
Volume50
Issue number3
DOIs
StatePublished - 1994

Fingerprint

Quasi-likelihood
Likelihood Methods
Biometrics
Binomial Distribution
Dose-response
dose response
Experiment
Likelihood
Beta-binomial Distribution
Experiments
Binary Response
Coverage Probability
biometry
methodology
Dose
Simulation Study
Dependent
dosage
Relationships

ASJC Scopus subject areas

  • Agricultural and Biological Sciences(all)
  • Public Health, Environmental and Occupational Health
  • Agricultural and Biological Sciences (miscellaneous)
  • Applied Mathematics
  • Statistics and Probability

Cite this

On the use of the quasi-likelihood method in teratological experiments. / Liang, K. Y.; Hanfell, J.

In: Biometrics, Vol. 50, No. 3, 1994, p. 872-880.

Research output: Contribution to journalArticle

Liang, K. Y. ; Hanfell, J. / On the use of the quasi-likelihood method in teratological experiments. In: Biometrics. 1994 ; Vol. 50, No. 3. pp. 872-880.
@article{63af90a624594c2dbcfe0ae274a95694,
title = "On the use of the quasi-likelihood method in teratological experiments",
abstract = "This paper concerns the impact of litter effects on the inference of dose- response relationships in teratological experiments with binary response. Kupper et al. (1986, Biometrics 42, 85-98) concluded that when intra-litter correlations are dose-dependent, the use of a common intra-litter correlation likelihood based on the beta-binomial distribution could lead to severe bias in estimation of the parameter β, which characterizes the dose-response relationship. We show here that the problems of bias and coverage probability for β could still be substantial when one uses the likelihood with heterogeneous intra-litter correlations. We then examine through a simulation study the performance of the quasi-likelihood method (Wedderburn, 1974, Biometrika 61, 439-447) and recommend that this method with a common intra- litter correlation parameter be used when the number of litters is small or modest.",
author = "Liang, {K. Y.} and J. Hanfell",
year = "1994",
doi = "10.2307/2532802",
language = "English (US)",
volume = "50",
pages = "872--880",
journal = "Biometrics",
issn = "0006-341X",
publisher = "Wiley-Blackwell",
number = "3",

}

TY - JOUR

T1 - On the use of the quasi-likelihood method in teratological experiments

AU - Liang, K. Y.

AU - Hanfell, J.

PY - 1994

Y1 - 1994

N2 - This paper concerns the impact of litter effects on the inference of dose- response relationships in teratological experiments with binary response. Kupper et al. (1986, Biometrics 42, 85-98) concluded that when intra-litter correlations are dose-dependent, the use of a common intra-litter correlation likelihood based on the beta-binomial distribution could lead to severe bias in estimation of the parameter β, which characterizes the dose-response relationship. We show here that the problems of bias and coverage probability for β could still be substantial when one uses the likelihood with heterogeneous intra-litter correlations. We then examine through a simulation study the performance of the quasi-likelihood method (Wedderburn, 1974, Biometrika 61, 439-447) and recommend that this method with a common intra- litter correlation parameter be used when the number of litters is small or modest.

AB - This paper concerns the impact of litter effects on the inference of dose- response relationships in teratological experiments with binary response. Kupper et al. (1986, Biometrics 42, 85-98) concluded that when intra-litter correlations are dose-dependent, the use of a common intra-litter correlation likelihood based on the beta-binomial distribution could lead to severe bias in estimation of the parameter β, which characterizes the dose-response relationship. We show here that the problems of bias and coverage probability for β could still be substantial when one uses the likelihood with heterogeneous intra-litter correlations. We then examine through a simulation study the performance of the quasi-likelihood method (Wedderburn, 1974, Biometrika 61, 439-447) and recommend that this method with a common intra- litter correlation parameter be used when the number of litters is small or modest.

UR - http://www.scopus.com/inward/record.url?scp=0028154818&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0028154818&partnerID=8YFLogxK

U2 - 10.2307/2532802

DO - 10.2307/2532802

M3 - Article

C2 - 7981409

AN - SCOPUS:0028154818

VL - 50

SP - 872

EP - 880

JO - Biometrics

JF - Biometrics

SN - 0006-341X

IS - 3

ER -