64th ISI World Statistics Congress - Ottawa, Canada

64th ISI World Statistics Congress - Ottawa, Canada

Spatial modeling of infectious diseases with covariates measurement error

Conference

64th ISI World Statistics Congress - Ottawa, Canada

Format: IPS Abstract

Keywords: expectation conditional maximization algorithm, geographically-dependent individual level model, infectious diseases, measurement error, susceptible-infected- removed model

Session: IPS 64 - Measurement Error Modeling: Advances and Applications

Tuesday 18 July 2 p.m. - 3:40 p.m. (Canada/Eastern)

Abstract

In spatial infectious disease models, it is typical to assume that only distance between susceptible and infectious individuals is important for modeling, but not the actual spatial locations of the individuals. Recently introduced geographically-dependent individual- level models (GD-ILMs) are used to also consider the effect of spatial locations of individuals and 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 occurrence of disease are measured accurately. There are many applications in which covariates are prone to measurement error. For instance, to study risk factors of influenza, people with low socio-economic status (SES) are known to be more at risk compared to the rest of population. However, the SES is prone to measurement error as it may not be accurately measured. In this talk, we propose a GD-ILM which accounts for measurement error in individual-level and area-level covariates. A Monte Carlo Expectation Conditional Maximization algorithm is used for inference. We use models fitted to data to predict the areas with high average infectivity rates. We evaluate the performance of proposed approach through simulation studies and by a real data application using influenza data in Manitoba, Canada.