Analysis of household data on influenza epidemic with Bayesian hierarchical model

C. Y. Hsu, A. M F Yen, L. S. Chen, H. H. Chen

Research output: Contribution to journalArticle

3 Citations (Scopus)

Abstract

Data used for modelling the household transmission of infectious diseases, such as influenza, have inherent multilevel structures and correlated property, which make the widely used conventional infectious disease transmission models (including the Greenwood model and the Reed-Frost model) not directly applicable within the context of a household (due to the crowded domestic condition or socioeconomic status of the household). Thus, at the household level, the effects resulting from individual-level factors, such as vaccination, may be confounded or modified in some way. We proposed the Bayesian hierarchical random-effects (random intercepts and random slopes) model under the context of generalised linear model to capture heterogeneity and variation on the individual, generation, and household levels. It was applied to empirical surveillance data on the influenza epidemic in Taiwan. The parameters of interest were estimated by using the Markov chain Monte Carlo method in conjunction with the Bayesian directed acyclic graphical models. Comparisons between models were made using the deviance information criterion. Based on the result of the random-slope Bayesian hierarchical method under the context of the Reed-Frost transmission model, the regression coefficient regarding the protective effect of vaccination varied statistically significantly from household to household. The result of such a heterogeneity was robust to the use of different prior distributions (including non-informative, sceptical, and enthusiastic ones). By integrating out the uncertainty of the parameters of the posterior distribution, the predictive distribution was computed to forecast the number of influenza cases allowing for random-household effect.

Original languageEnglish
Pages (from-to)13-26
Number of pages14
JournalMathematical Biosciences
Volume261
DOIs
Publication statusPublished - Mar 1 2015

Fingerprint

Bayesian Hierarchical Model
Influenza
influenza
Human Influenza
households
Vaccination
Infectious Diseases
Random Effects
Infectious Disease Transmission
Slope
frost
Model
Deviance Information Criterion
infectious diseases
Predictive Distribution
Markov Chain Monte Carlo Methods
vaccination
Intercept
Taiwan
Generalized Linear Model

Keywords

  • Bayesian hierarchical model
  • Chain binomial model
  • Infectious disease
  • Influenza

ASJC Scopus subject areas

  • Applied Mathematics
  • Statistics and Probability
  • Modelling and Simulation
  • Agricultural and Biological Sciences(all)
  • Biochemistry, Genetics and Molecular Biology(all)
  • Immunology and Microbiology(all)
  • Medicine(all)

Cite this

Analysis of household data on influenza epidemic with Bayesian hierarchical model. / Hsu, C. Y.; Yen, A. M F; Chen, L. S.; Chen, H. H.

In: Mathematical Biosciences, Vol. 261, 01.03.2015, p. 13-26.

Research output: Contribution to journalArticle

@article{ab24f179e5034a86a791bca1147f4333,
title = "Analysis of household data on influenza epidemic with Bayesian hierarchical model",
abstract = "Data used for modelling the household transmission of infectious diseases, such as influenza, have inherent multilevel structures and correlated property, which make the widely used conventional infectious disease transmission models (including the Greenwood model and the Reed-Frost model) not directly applicable within the context of a household (due to the crowded domestic condition or socioeconomic status of the household). Thus, at the household level, the effects resulting from individual-level factors, such as vaccination, may be confounded or modified in some way. We proposed the Bayesian hierarchical random-effects (random intercepts and random slopes) model under the context of generalised linear model to capture heterogeneity and variation on the individual, generation, and household levels. It was applied to empirical surveillance data on the influenza epidemic in Taiwan. The parameters of interest were estimated by using the Markov chain Monte Carlo method in conjunction with the Bayesian directed acyclic graphical models. Comparisons between models were made using the deviance information criterion. Based on the result of the random-slope Bayesian hierarchical method under the context of the Reed-Frost transmission model, the regression coefficient regarding the protective effect of vaccination varied statistically significantly from household to household. The result of such a heterogeneity was robust to the use of different prior distributions (including non-informative, sceptical, and enthusiastic ones). By integrating out the uncertainty of the parameters of the posterior distribution, the predictive distribution was computed to forecast the number of influenza cases allowing for random-household effect.",
keywords = "Bayesian hierarchical model, Chain binomial model, Infectious disease, Influenza",
author = "Hsu, {C. Y.} and Yen, {A. M F} and Chen, {L. S.} and Chen, {H. H.}",
year = "2015",
month = "3",
day = "1",
doi = "10.1016/j.mbs.2014.11.006",
language = "English",
volume = "261",
pages = "13--26",
journal = "Mathematical Biosciences",
issn = "0025-5564",
publisher = "Elsevier Inc.",

}

TY - JOUR

T1 - Analysis of household data on influenza epidemic with Bayesian hierarchical model

AU - Hsu, C. Y.

AU - Yen, A. M F

AU - Chen, L. S.

AU - Chen, H. H.

PY - 2015/3/1

Y1 - 2015/3/1

N2 - Data used for modelling the household transmission of infectious diseases, such as influenza, have inherent multilevel structures and correlated property, which make the widely used conventional infectious disease transmission models (including the Greenwood model and the Reed-Frost model) not directly applicable within the context of a household (due to the crowded domestic condition or socioeconomic status of the household). Thus, at the household level, the effects resulting from individual-level factors, such as vaccination, may be confounded or modified in some way. We proposed the Bayesian hierarchical random-effects (random intercepts and random slopes) model under the context of generalised linear model to capture heterogeneity and variation on the individual, generation, and household levels. It was applied to empirical surveillance data on the influenza epidemic in Taiwan. The parameters of interest were estimated by using the Markov chain Monte Carlo method in conjunction with the Bayesian directed acyclic graphical models. Comparisons between models were made using the deviance information criterion. Based on the result of the random-slope Bayesian hierarchical method under the context of the Reed-Frost transmission model, the regression coefficient regarding the protective effect of vaccination varied statistically significantly from household to household. The result of such a heterogeneity was robust to the use of different prior distributions (including non-informative, sceptical, and enthusiastic ones). By integrating out the uncertainty of the parameters of the posterior distribution, the predictive distribution was computed to forecast the number of influenza cases allowing for random-household effect.

AB - Data used for modelling the household transmission of infectious diseases, such as influenza, have inherent multilevel structures and correlated property, which make the widely used conventional infectious disease transmission models (including the Greenwood model and the Reed-Frost model) not directly applicable within the context of a household (due to the crowded domestic condition or socioeconomic status of the household). Thus, at the household level, the effects resulting from individual-level factors, such as vaccination, may be confounded or modified in some way. We proposed the Bayesian hierarchical random-effects (random intercepts and random slopes) model under the context of generalised linear model to capture heterogeneity and variation on the individual, generation, and household levels. It was applied to empirical surveillance data on the influenza epidemic in Taiwan. The parameters of interest were estimated by using the Markov chain Monte Carlo method in conjunction with the Bayesian directed acyclic graphical models. Comparisons between models were made using the deviance information criterion. Based on the result of the random-slope Bayesian hierarchical method under the context of the Reed-Frost transmission model, the regression coefficient regarding the protective effect of vaccination varied statistically significantly from household to household. The result of such a heterogeneity was robust to the use of different prior distributions (including non-informative, sceptical, and enthusiastic ones). By integrating out the uncertainty of the parameters of the posterior distribution, the predictive distribution was computed to forecast the number of influenza cases allowing for random-household effect.

KW - Bayesian hierarchical model

KW - Chain binomial model

KW - Infectious disease

KW - Influenza

UR - http://www.scopus.com/inward/record.url?scp=84961381514&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84961381514&partnerID=8YFLogxK

U2 - 10.1016/j.mbs.2014.11.006

DO - 10.1016/j.mbs.2014.11.006

M3 - Article

C2 - 25484132

AN - SCOPUS:84961381514

VL - 261

SP - 13

EP - 26

JO - Mathematical Biosciences

JF - Mathematical Biosciences

SN - 0025-5564

ER -