GDILM_SEIRS_Par_Est: GDILM SEIRS for Real Data

In GDILM.SEIRS: Spatial Modeling of Infectious Disease with Reinfection

GDILM SEIRS for Real Data

Description

This function applies the Geographically Dependent Individual Level Model (GDILM) for infectious disease transmission, incorporating reinfection dynamics within the Susceptible-Exposed-Infectious-Recovered-Susceptible (SEIRS) framework, to real data. It employs a likelihood based Monte Carlo Expectation Conditional Maximization (MCECM) algorithm for parameter estimation and AIC calculation. This function requires two dataframes, named data and adjacency_matrix, along with the necessary parameters. Detailed information on the structure of these two datasets is provided in the package.

Usage

GDILM_SEIRS_Par_Est(
  data,
  adjacency_matrix,
  DimCovInf,
  DimCovSus,
  DimCovSusReInf,
  tau0,
  lambda0,
  alphaS0,
  delta0,
  alphaT0,
  InfPrd,
  IncPrd,
  NIterMC,
  NIterMCECM
)

Arguments

data	Dataset. The dataset should exactly match the data file in the data folder, including all the columns with the same names.
adjacency_matrix	Adjacency matrix representing the regions in the study area (0 if no connection between regions)
DimCovInf	Dimensions of the individual infectivity covariate
DimCovSus	Dimensions of the area-level susceptibility to initial infection covariate
DimCovSusReInf	Dimensions of the area-level susceptibility to reinfection covariate
tau0	Initial value for spatial precision
lambda0	Initial value for spatial dependence
alphaS0	Initial value for the susceptibility intercept
delta0	Initial value for the spatial decay parameter
alphaT0	Initial value for the infectivity intercept
InfPrd	Infectious period that can be obtained either from the literature or by fitting an SEIRS model to the data
IncPrd	Incubation period that can be obtained either from the literature or by fitting an SEIRS model to the data
NIterMC	Number of MCMC iterations
NIterMCECM	Number of MCECM iterations

Value

alphaS Estimate of alpha S

BetaCovInf Estimate of beta vector for the individual level infection covariate

BetaCovSus Estimate of beta vector for the areal susceptibility to first infection covariate

BetaCovSusReInf Estimate of beta vector for the areal susceptibility to reinfection covariate

alphaT Estimate of alpha T

delta Estimate of delta

tau1 Estimate of tau

lambda1 Estimate of lambda

AIC AIC of the fitted GDILM SEIRS

References

Abed, A., Torabi, M., & Mashreghi, Z. (2025). Individual level modeling of infectious disease transmission with reinfection dynamics: Application to Tuberculosis in Manitoba, Canada. Spatial and Spatio-Temporal Epidemiology, 100780.

Examples

data(data)
data(adjacency_matrix)
# alphaS0 and alphaT0 must be small enough to keep the infection probabilities
# away from 1; otherwise every probability is numerically 1, the second-order
# terms carry no information and the intercepts cannot be estimated.
GDILM_SEIRS_Par_Est(data,adjacency_matrix,2,2,2,0.5, 0.5, -20, 2, -3, 1, 1, 20, 2)

GDILM.SEIRS documentation built on Sept. 7, 2026, 1:07 a.m.