A mixture model for bovine abortion and foetal survival

Timothy Hanson, Edward J. Bedrick, Wesley O. Johnson, Mark Thurmond

Research output: Contribution to journalArticle

18 Citations (Scopus)

Abstract

The effect of spontaneous abortion on the dairy industry is substantial, costing the industry on the order of $200 million per year in California alone. We analyse data from a cohort study of nine dairy herds in Central California. A key feature of the analysis is the observation that only a relatively small proportion of cows will abort (around 10-15 per cent), so that it is inappropriate to analyse the time-to-abortion (TTA) data as if it were standard censored survival data, with cows that fail to abort by the end of the study treated as censored observations. We thus broaden the scope to consider the analysis of foetal lifetime distribution (FLD) data for the cows, with the dual goals of characterizing the effects of various risk factors on (i) the likelihood of abortion and, conditional on abortion status, on (ii) the risk of early versus late abortion. A single model is developed to accomplish both goals with two sets of specific herd effects modelled as random effects. Because multimodal foetal hazard functions are expected for the TTA data, both a parametric mixture model and a non-parametric model are developed. Furthermore, the two sets of analyses are linked because of anticipated dependence between the random herd effects. All modelling and inferences are accomplished using modern Bayesian methods.

Original languageEnglish (US)
Pages (from-to)1725-1739
Number of pages15
JournalStatistics in Medicine
Volume22
Issue number10
DOIs
StatePublished - May 30 2003

Fingerprint

Mixture Model
Dairying
Bayes Theorem
Spontaneous Abortion
Random Effects
Industry
Cohort Studies
Censored Survival Data
Censored Observations
Multimodal Function
Cohort Study
Lifetime Distribution
Hazard Function
Nonparametric Model
Bayesian Methods
Risk Factors
Parametric Model
Likelihood
Proportion
Modeling

Keywords

  • Accelerated failure time model
  • Bayesian inference
  • Cox model
  • Logistic regression

ASJC Scopus subject areas

  • Epidemiology
  • Statistics and Probability

Cite this

A mixture model for bovine abortion and foetal survival. / Hanson, Timothy; Bedrick, Edward J.; Johnson, Wesley O.; Thurmond, Mark.

In: Statistics in Medicine, Vol. 22, No. 10, 30.05.2003, p. 1725-1739.

Research output: Contribution to journalArticle

Hanson, Timothy ; Bedrick, Edward J. ; Johnson, Wesley O. ; Thurmond, Mark. / A mixture model for bovine abortion and foetal survival. In: Statistics in Medicine. 2003 ; Vol. 22, No. 10. pp. 1725-1739.
@article{4d8528b1016847a48af7b221340516ef,
title = "A mixture model for bovine abortion and foetal survival",
abstract = "The effect of spontaneous abortion on the dairy industry is substantial, costing the industry on the order of $200 million per year in California alone. We analyse data from a cohort study of nine dairy herds in Central California. A key feature of the analysis is the observation that only a relatively small proportion of cows will abort (around 10-15 per cent), so that it is inappropriate to analyse the time-to-abortion (TTA) data as if it were standard censored survival data, with cows that fail to abort by the end of the study treated as censored observations. We thus broaden the scope to consider the analysis of foetal lifetime distribution (FLD) data for the cows, with the dual goals of characterizing the effects of various risk factors on (i) the likelihood of abortion and, conditional on abortion status, on (ii) the risk of early versus late abortion. A single model is developed to accomplish both goals with two sets of specific herd effects modelled as random effects. Because multimodal foetal hazard functions are expected for the TTA data, both a parametric mixture model and a non-parametric model are developed. Furthermore, the two sets of analyses are linked because of anticipated dependence between the random herd effects. All modelling and inferences are accomplished using modern Bayesian methods.",
keywords = "Accelerated failure time model, Bayesian inference, Cox model, Logistic regression",
author = "Timothy Hanson and Bedrick, {Edward J.} and Johnson, {Wesley O.} and Mark Thurmond",
year = "2003",
month = "5",
day = "30",
doi = "10.1002/sim.1376",
language = "English (US)",
volume = "22",
pages = "1725--1739",
journal = "Statistics in Medicine",
issn = "0277-6715",
publisher = "John Wiley and Sons Ltd",
number = "10",

}

TY - JOUR

T1 - A mixture model for bovine abortion and foetal survival

AU - Hanson, Timothy

AU - Bedrick, Edward J.

AU - Johnson, Wesley O.

AU - Thurmond, Mark

PY - 2003/5/30

Y1 - 2003/5/30

N2 - The effect of spontaneous abortion on the dairy industry is substantial, costing the industry on the order of $200 million per year in California alone. We analyse data from a cohort study of nine dairy herds in Central California. A key feature of the analysis is the observation that only a relatively small proportion of cows will abort (around 10-15 per cent), so that it is inappropriate to analyse the time-to-abortion (TTA) data as if it were standard censored survival data, with cows that fail to abort by the end of the study treated as censored observations. We thus broaden the scope to consider the analysis of foetal lifetime distribution (FLD) data for the cows, with the dual goals of characterizing the effects of various risk factors on (i) the likelihood of abortion and, conditional on abortion status, on (ii) the risk of early versus late abortion. A single model is developed to accomplish both goals with two sets of specific herd effects modelled as random effects. Because multimodal foetal hazard functions are expected for the TTA data, both a parametric mixture model and a non-parametric model are developed. Furthermore, the two sets of analyses are linked because of anticipated dependence between the random herd effects. All modelling and inferences are accomplished using modern Bayesian methods.

AB - The effect of spontaneous abortion on the dairy industry is substantial, costing the industry on the order of $200 million per year in California alone. We analyse data from a cohort study of nine dairy herds in Central California. A key feature of the analysis is the observation that only a relatively small proportion of cows will abort (around 10-15 per cent), so that it is inappropriate to analyse the time-to-abortion (TTA) data as if it were standard censored survival data, with cows that fail to abort by the end of the study treated as censored observations. We thus broaden the scope to consider the analysis of foetal lifetime distribution (FLD) data for the cows, with the dual goals of characterizing the effects of various risk factors on (i) the likelihood of abortion and, conditional on abortion status, on (ii) the risk of early versus late abortion. A single model is developed to accomplish both goals with two sets of specific herd effects modelled as random effects. Because multimodal foetal hazard functions are expected for the TTA data, both a parametric mixture model and a non-parametric model are developed. Furthermore, the two sets of analyses are linked because of anticipated dependence between the random herd effects. All modelling and inferences are accomplished using modern Bayesian methods.

KW - Accelerated failure time model

KW - Bayesian inference

KW - Cox model

KW - Logistic regression

UR - http://www.scopus.com/inward/record.url?scp=0038025641&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0038025641&partnerID=8YFLogxK

U2 - 10.1002/sim.1376

DO - 10.1002/sim.1376

M3 - Article

C2 - 12720307

AN - SCOPUS:0038025641

VL - 22

SP - 1725

EP - 1739

JO - Statistics in Medicine

JF - Statistics in Medicine

SN - 0277-6715

IS - 10

ER -