Assessing overdispersion and dose-response in the male dominant lethal assay

Ann Marie C Lockhart, Walter W Piegorsch, Jack B. Bishop

Research output: Contribution to journalArticle

23 Citations (Scopus)

Abstract

In dominant lethal studies the primary variables of interest are typically expressed as discrete counts or proportions (e.g., live implants, resorptions, percent pregnant). Simple statistical sampling models for discrete data such as binomial or Poisson generally do not fit this type of data because of extra-binomial or extra-Poisson departures from variability predicted under these simple models. Extra-variability in the fetal response may originate from parental contributions. These can lead to over- or under-dispersion seen as, e.g., extra-binomial variability in the proportion response. Utilizing a large control database, we investigated the relative impact of extra-variability from male or female contributions on the endpoints of interest. Male-related effects did not seem to contribute to overdispersion in our database; female-related effects were, however, evidenced. Various statistical methods were considered to test for significant treatment differences under these forms of sampling variability. Computer simulations were used to evaluate these methods and to determine which are most appropriate for practical use in the evaluation of dominant lethal data. Our results suggest that distribution-free statistical methods such as a nonparametric permutation test or rank-based tests for trend can be recommended for use.

Original languageEnglish (US)
Pages (from-to)35-58
Number of pages24
JournalMutation Research/Environmental Mutagenesis and Related Subjects
Volume272
Issue number1
DOIs
StatePublished - 1992
Externally publishedYes

Fingerprint

Assays
Statistical methods
Sampling
Databases
Statistical Distributions
Statistical Models
Computer Simulation
Computer simulation

Keywords

  • Dose-response analysis
  • Extra-binomial variability
  • Germ-cell mutagenesis
  • Heritable disease
  • Litter effect
  • Mouse
  • Statistical methods
  • Under-dispersion

ASJC Scopus subject areas

  • Genetics
  • Toxicology
  • Medicine(all)

Cite this

Assessing overdispersion and dose-response in the male dominant lethal assay. / Lockhart, Ann Marie C; Piegorsch, Walter W; Bishop, Jack B.

In: Mutation Research/Environmental Mutagenesis and Related Subjects, Vol. 272, No. 1, 1992, p. 35-58.

Research output: Contribution to journalArticle

@article{0878877a26234f768f2a05214122aa22,
title = "Assessing overdispersion and dose-response in the male dominant lethal assay",
abstract = "In dominant lethal studies the primary variables of interest are typically expressed as discrete counts or proportions (e.g., live implants, resorptions, percent pregnant). Simple statistical sampling models for discrete data such as binomial or Poisson generally do not fit this type of data because of extra-binomial or extra-Poisson departures from variability predicted under these simple models. Extra-variability in the fetal response may originate from parental contributions. These can lead to over- or under-dispersion seen as, e.g., extra-binomial variability in the proportion response. Utilizing a large control database, we investigated the relative impact of extra-variability from male or female contributions on the endpoints of interest. Male-related effects did not seem to contribute to overdispersion in our database; female-related effects were, however, evidenced. Various statistical methods were considered to test for significant treatment differences under these forms of sampling variability. Computer simulations were used to evaluate these methods and to determine which are most appropriate for practical use in the evaluation of dominant lethal data. Our results suggest that distribution-free statistical methods such as a nonparametric permutation test or rank-based tests for trend can be recommended for use.",
keywords = "Dose-response analysis, Extra-binomial variability, Germ-cell mutagenesis, Heritable disease, Litter effect, Mouse, Statistical methods, Under-dispersion",
author = "Lockhart, {Ann Marie C} and Piegorsch, {Walter W} and Bishop, {Jack B.}",
year = "1992",
doi = "10.1016/0165-1161(92)90007-9",
language = "English (US)",
volume = "272",
pages = "35--58",
journal = "Mutation Research - Environmental Mutagenesis and Related Subjects Including Methodology",
issn = "0165-1161",
publisher = "Elsevier BV",
number = "1",

}

TY - JOUR

T1 - Assessing overdispersion and dose-response in the male dominant lethal assay

AU - Lockhart, Ann Marie C

AU - Piegorsch, Walter W

AU - Bishop, Jack B.

PY - 1992

Y1 - 1992

N2 - In dominant lethal studies the primary variables of interest are typically expressed as discrete counts or proportions (e.g., live implants, resorptions, percent pregnant). Simple statistical sampling models for discrete data such as binomial or Poisson generally do not fit this type of data because of extra-binomial or extra-Poisson departures from variability predicted under these simple models. Extra-variability in the fetal response may originate from parental contributions. These can lead to over- or under-dispersion seen as, e.g., extra-binomial variability in the proportion response. Utilizing a large control database, we investigated the relative impact of extra-variability from male or female contributions on the endpoints of interest. Male-related effects did not seem to contribute to overdispersion in our database; female-related effects were, however, evidenced. Various statistical methods were considered to test for significant treatment differences under these forms of sampling variability. Computer simulations were used to evaluate these methods and to determine which are most appropriate for practical use in the evaluation of dominant lethal data. Our results suggest that distribution-free statistical methods such as a nonparametric permutation test or rank-based tests for trend can be recommended for use.

AB - In dominant lethal studies the primary variables of interest are typically expressed as discrete counts or proportions (e.g., live implants, resorptions, percent pregnant). Simple statistical sampling models for discrete data such as binomial or Poisson generally do not fit this type of data because of extra-binomial or extra-Poisson departures from variability predicted under these simple models. Extra-variability in the fetal response may originate from parental contributions. These can lead to over- or under-dispersion seen as, e.g., extra-binomial variability in the proportion response. Utilizing a large control database, we investigated the relative impact of extra-variability from male or female contributions on the endpoints of interest. Male-related effects did not seem to contribute to overdispersion in our database; female-related effects were, however, evidenced. Various statistical methods were considered to test for significant treatment differences under these forms of sampling variability. Computer simulations were used to evaluate these methods and to determine which are most appropriate for practical use in the evaluation of dominant lethal data. Our results suggest that distribution-free statistical methods such as a nonparametric permutation test or rank-based tests for trend can be recommended for use.

KW - Dose-response analysis

KW - Extra-binomial variability

KW - Germ-cell mutagenesis

KW - Heritable disease

KW - Litter effect

KW - Mouse

KW - Statistical methods

KW - Under-dispersion

UR - http://www.scopus.com/inward/record.url?scp=0026686315&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0026686315&partnerID=8YFLogxK

U2 - 10.1016/0165-1161(92)90007-9

DO - 10.1016/0165-1161(92)90007-9

M3 - Article

VL - 272

SP - 35

EP - 58

JO - Mutation Research - Environmental Mutagenesis and Related Subjects Including Methodology

JF - Mutation Research - Environmental Mutagenesis and Related Subjects Including Methodology

SN - 0165-1161

IS - 1

ER -