Online Program Home
  My Program

All Times EDT

Abstract Details

Activity Number: 101 - Recent Advances in Statistical Modeling of Infectious Diseases
Type: Invited
Date/Time: Monday, August 3, 2020 : 1:00 PM to 2:50 PM
Sponsor: SSC (Statistical Society of Canada)
Abstract #309180
Title: Inference for Individual-Level Models of Infectious Diseases with Covariates Measurement Error
Author(s): Leila Amiri* and Mahmoud Torabi and Rob Deardon
Companies: University of Manitoba and University of Manitoba and University of Calgary
Keywords: Conditional autoregressive model; Expectation Conditional Maximization algorithm; Individual-level models; Susceptible-infected-removed model; Measurement error ; Geographically-dependent individual level models

Geographically-dependent individual-level models (GD-ILMs) are statistical models to identify infectious disease dynamic which allow us to consider the effect of the spatial locations of individuals, and also the distance between susceptible and infectious individuals for determining the risk of infection. In these models, it is assumed that the covariates used to predict the outbreak and transmission of diseases are measured accurately. However, there are many applications that the covariates are prone to measurement error. For instance, census covariates such as indigenous and socio-economic status, which are measured with error, are used as risk factors for influenza. In this talk, we propose a GD-ILM which also accounts for the individual-level and area-level covariates measurement error. Monte Carlo Expectation Conditional Maximization (MCECM) algorithm is used for inference. Estimated parameters using MCECM enable us to predict the areas with the highest average infectivity rates. We evaluate the performance of the proposed approach through simulation studies and also by a real data application of influenza data in Manitoba, Canada.

Authors who are presenting talks have a * after their name.

Back to the full JSM 2020 program