A Network-based Analysis of the 1861 Hagelloch Measles Data

Chris Groendyke, David Welch, David R. Hunter

Research output: Contribution to journalArticle

25 Citations (Scopus)

Abstract

In this article, we demonstrate a statistical method for fitting the parameters of a sophisticated network and epidemic model to disease data. The pattern of contacts between hosts is described by a class of dyadic independence exponential-family random graph models (ERGMs), whereas the transmission process that runs over the network is modeled as a stochastic susceptible-exposed-infectious-removed (SEIR) epidemic. We fit these models to very detailed data from the 1861 measles outbreak in Hagelloch, Germany. The network models include parameters for all recorded host covariates including age, sex, household, and classroom membership and household location whereas the SEIR epidemic model has exponentially distributed transmission times with gamma-distributed latent and infective periods. This approach allows us to make meaningful statements about the structure of the population-separate from the transmission process-as well as to provide estimates of various biological quantities of interest, such as the effective reproductive number, R. Using reversible jump Markov chain Monte Carlo, we produce samples from the joint posterior distribution of all the parameters of this model-the network, transmission tree, network parameters, and SEIR parameters-and perform Bayesian model selection to find the best-fitting network model. We compare our results with those of previous analyses and show that the ERGM network model better fits the data than a Bernoulli network model previously used. We also provide a software package, written in R, that performs this type of analysis.

Original languageEnglish (US)
Pages (from-to)755-765
Number of pages11
JournalBiometrics
Volume68
Issue number3
DOIs
StatePublished - Sep 1 2012

Fingerprint

Measles
Network Model
Exponential Family
Epidemic Model
Graph Model
Markov Chains
Random Graphs
Disease Outbreaks
Germany
Reproductive number
Reversible Jump Markov Chain Monte Carlo
Bayesian Model Selection
Software
Tree Networks
Posterior distribution
Bernoulli
Joint Distribution
Software Package
Statistical method
Covariates

All Science Journal Classification (ASJC) codes

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

Cite this

Groendyke, Chris ; Welch, David ; Hunter, David R. / A Network-based Analysis of the 1861 Hagelloch Measles Data. In: Biometrics. 2012 ; Vol. 68, No. 3. pp. 755-765.
@article{9e7e9c8ac71545dfb9fae78686313ca0,
title = "A Network-based Analysis of the 1861 Hagelloch Measles Data",
abstract = "In this article, we demonstrate a statistical method for fitting the parameters of a sophisticated network and epidemic model to disease data. The pattern of contacts between hosts is described by a class of dyadic independence exponential-family random graph models (ERGMs), whereas the transmission process that runs over the network is modeled as a stochastic susceptible-exposed-infectious-removed (SEIR) epidemic. We fit these models to very detailed data from the 1861 measles outbreak in Hagelloch, Germany. The network models include parameters for all recorded host covariates including age, sex, household, and classroom membership and household location whereas the SEIR epidemic model has exponentially distributed transmission times with gamma-distributed latent and infective periods. This approach allows us to make meaningful statements about the structure of the population-separate from the transmission process-as well as to provide estimates of various biological quantities of interest, such as the effective reproductive number, R. Using reversible jump Markov chain Monte Carlo, we produce samples from the joint posterior distribution of all the parameters of this model-the network, transmission tree, network parameters, and SEIR parameters-and perform Bayesian model selection to find the best-fitting network model. We compare our results with those of previous analyses and show that the ERGM network model better fits the data than a Bernoulli network model previously used. We also provide a software package, written in R, that performs this type of analysis.",
author = "Chris Groendyke and David Welch and Hunter, {David R.}",
year = "2012",
month = "9",
day = "1",
doi = "10.1111/j.1541-0420.2012.01748.x",
language = "English (US)",
volume = "68",
pages = "755--765",
journal = "Biometrics",
issn = "0006-341X",
publisher = "Wiley-Blackwell",
number = "3",

}

A Network-based Analysis of the 1861 Hagelloch Measles Data. / Groendyke, Chris; Welch, David; Hunter, David R.

In: Biometrics, Vol. 68, No. 3, 01.09.2012, p. 755-765.

Research output: Contribution to journalArticle

TY - JOUR

T1 - A Network-based Analysis of the 1861 Hagelloch Measles Data

AU - Groendyke, Chris

AU - Welch, David

AU - Hunter, David R.

PY - 2012/9/1

Y1 - 2012/9/1

N2 - In this article, we demonstrate a statistical method for fitting the parameters of a sophisticated network and epidemic model to disease data. The pattern of contacts between hosts is described by a class of dyadic independence exponential-family random graph models (ERGMs), whereas the transmission process that runs over the network is modeled as a stochastic susceptible-exposed-infectious-removed (SEIR) epidemic. We fit these models to very detailed data from the 1861 measles outbreak in Hagelloch, Germany. The network models include parameters for all recorded host covariates including age, sex, household, and classroom membership and household location whereas the SEIR epidemic model has exponentially distributed transmission times with gamma-distributed latent and infective periods. This approach allows us to make meaningful statements about the structure of the population-separate from the transmission process-as well as to provide estimates of various biological quantities of interest, such as the effective reproductive number, R. Using reversible jump Markov chain Monte Carlo, we produce samples from the joint posterior distribution of all the parameters of this model-the network, transmission tree, network parameters, and SEIR parameters-and perform Bayesian model selection to find the best-fitting network model. We compare our results with those of previous analyses and show that the ERGM network model better fits the data than a Bernoulli network model previously used. We also provide a software package, written in R, that performs this type of analysis.

AB - In this article, we demonstrate a statistical method for fitting the parameters of a sophisticated network and epidemic model to disease data. The pattern of contacts between hosts is described by a class of dyadic independence exponential-family random graph models (ERGMs), whereas the transmission process that runs over the network is modeled as a stochastic susceptible-exposed-infectious-removed (SEIR) epidemic. We fit these models to very detailed data from the 1861 measles outbreak in Hagelloch, Germany. The network models include parameters for all recorded host covariates including age, sex, household, and classroom membership and household location whereas the SEIR epidemic model has exponentially distributed transmission times with gamma-distributed latent and infective periods. This approach allows us to make meaningful statements about the structure of the population-separate from the transmission process-as well as to provide estimates of various biological quantities of interest, such as the effective reproductive number, R. Using reversible jump Markov chain Monte Carlo, we produce samples from the joint posterior distribution of all the parameters of this model-the network, transmission tree, network parameters, and SEIR parameters-and perform Bayesian model selection to find the best-fitting network model. We compare our results with those of previous analyses and show that the ERGM network model better fits the data than a Bernoulli network model previously used. We also provide a software package, written in R, that performs this type of analysis.

UR - http://www.scopus.com/inward/record.url?scp=84866748157&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84866748157&partnerID=8YFLogxK

U2 - 10.1111/j.1541-0420.2012.01748.x

DO - 10.1111/j.1541-0420.2012.01748.x

M3 - Article

C2 - 22364540

AN - SCOPUS:84866748157

VL - 68

SP - 755

EP - 765

JO - Biometrics

JF - Biometrics

SN - 0006-341X

IS - 3

ER -