Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Experiment Videos

Modelling overdispersion in toxicological mortality data grouped over time

R J Hines1, J F Lawless

  • 1Department of Statistics and Actuarial Science, University of Waterloo, Ontario, Canada.

Biometrics
|March 1, 1993
PubMed
Summary

Toxicologists can analyze animal toxicity data using generalized linear models that account for extra-multinomial variation. This study extends existing models to improve the analysis of grouped animal mortality experiments.

Related Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

HostSeq: a Canadian whole genome sequencing and clinical data resource.

BMC genomic data·2023
Same author

Two-phase outcome-dependent studies for failure times and testing for effects of expensive covariates.

Lifetime data analysis·2016
Same author

Estimation of state occupancy probabilities in multistate models with dependent intermittent observation, with application to HIV viral rebounds.

Statistics in medicine·2016
Same author

Estimation and assessment of markov multistate models with intermittent observations on individuals.

Lifetime data analysis·2014
Same author

Estimation of finite population duration distributions from longitudinal survey panels with intermittent followup.

Lifetime data analysis·2013
Same author

Estimation of distribution function in bivariate competing risk models.

Biometrical journal. Biometrische Zeitschrift·2006

Area of Science:

  • Toxicology
  • Biostatistics
  • Statistical Modeling

Background:

  • Toxicity experiments often involve grouped animal data with mortality measured over time.
  • Existing methods like survival analysis and generalized linear models (GLMs) have limitations with grouped data.
  • Extra-multinomial variation (overdispersion) is a common issue in such experiments due to the use of animal groups.

Purpose of the Study:

  • To propose and evaluate overdispersion models for generalized linear models (GLMs) applied to multinomial toxicity data.
  • To extend existing binomial overdispersion models to the multinomial case.
  • To compare robust asymptotic covariance matrix estimators with model-based estimators for regression parameters.

Main Methods:

  • Incorporation of overdispersion models into the generalized linear model framework for multinomial data.

Related Experiment Videos

  • Adaptation of binomial overdispersion models (Williams, Moore) for multinomial data.
  • Examination and comparison of robust asymptotic covariance matrix estimators (Liang & Zeger, Zeger & Liang) with model-based estimators.

    • Main Results:

    • The study presents extensions of binomial overdispersion models for multinomial toxicity data.
    • It evaluates robust covariance matrix estimators against model-based ones.
    • The research provides recommendations for the analysis of grouped animal toxicity data.

    Conclusions:

    • Generalized linear models with appropriate overdispersion models can effectively analyze grouped animal toxicity data.
    • The proposed models and robust estimators offer improved analytical approaches for toxicologists.
    • Careful consideration of experimental unit (animal groups) is crucial for accurate statistical inference in toxicity studies.