|
Rob Deardon Person1 #679869 Associate Professor in the Department of Production Animal Health in the Faculty of Veterinary Medicine and the Department of Mathematics and Statistics in the Faculty of Science at the University of Calgary. | 
Current Research Interests1. STATISTICAL MODELING OF INFECTIOUS DISEASE - Diseases of humans, animals and plants
- Spatial systems
- Network-based systems
- Measurement error & latent information
- Robustness to assumptions
- Computational methodologies (see Bayesian & Computational Statistics below)
- Study design
- Model comparison
- Model adequacy/goodness of fit
- Disease surveillance models
2. BAYESIAN AND COMPUTATIONAL STATISTICS - Markov chain Monte Carlo methods (MCMC)
- Approximate Bayesian computation (ABC)
- Gaussian process emulation
- Machine learning-based approximate inference
- Importance sampling and sequential Monte Carlo (SMC)
3. ECOLOGICAL AND ENVIRONMENTAL MODELING - Spatial and spatiotemporal models (e.g. disease mapping)
- Invasive species models (e.g. Ash borer, Pine beetle, Giant hogweed)
- Fire spread models
- Animal movement models
4. EXPERIMENTAL DESIGN - Bayesian experimental design
- Crop trials (e.g. dealing with inter-plot interference in experiments on crop diseases)
- Spatial design for experiments used to ascertain infectious disease dynamics
- Response surface methodology and optimal design
5. STATISTICAL & MACHINE LEARNING - Random forests & ensemble methods
- Networks and deep learning
- High dimensional model selection (e.g. gene selection)
- Predictive modelling and classification
6. OTHER TOPICS - Bayesian clinical trials
- Network meta-analyses
- Discrete choice experiments
Tags: Robert Deardon |
+Citations (3) - CitationsAdd new citationList by: CiterankMapLink[2] A Framework for Incorporating Behavioural Change into Individual-Level Spatial Epidemic Models
Author: Madeline A. Ward, Rob Deardon, Lorna E. Deeth Publication date: 1 August 2023 Publication info: arXiv:2308.00815v1 [stat.ME] Cited by: David Price 10:29 PM 16 November 2023 GMT Citerank: (2) 715386Madeline WardMadeline A. Ward is a PHD student in Biostatistics in the Department of Mathematics and Statistics at the University of Calgary.10019D3ABAB, 715387SMMEID – Publications144B5ACA0 URL: DOI: https://doi.org/10.48550/arXiv.2308.00815
| Excerpt / Summary [arXiv, 1 August 2023]
During epidemics, people will often modify their behaviour patterns over time in response to changes in their perceived risk of spreading or contracting the disease. This can substantially impact the trajectory of the epidemic. However, most infectious disease models assume stable population behaviour due to the challenges of modelling these changes. We present a flexible new class of models, called behavioural change individual-level models (BC-ILMs), that incorporate both individual-level covariate information and a data-driven behavioural change effect. Focusing on spatial BC-ILMs, we consider four "alarm" functions to model the effect of behavioural change as a function of infection prevalence over time. We show how these models can be estimated in a simulation setting. We investigate the impact of misspecifying the alarm function when fitting a BC-ILM, and find that if behavioural change is present in a population, using an incorrect alarm function will still result in an improvement in posterior predictive performance over a model that assumes stable population behaviour. We also find that using spike and slab priors on alarm function parameters is a simple and effective method to determine whether a behavioural change effect is present in a population. Finally, we show results from fitting spatial BC-ILMs to data from the 2001 U.K. foot and mouth disease epidemic. |
Link[3] Bayesian modeling of dynamic behavioral change during an epidemic
Author: Caitlin Ward, Rob Deardon, Alexandra M. Schmidt Publication date: 11 August 2023 Publication info: Infectious Disease Modelling, Volume 8, Issue 4,
2023, Pages 947-963, ISSN 2468-0427, Cited by: David Price 10:36 PM 16 November 2023 GMT Citerank: (1) 715387SMMEID – Publications144B5ACA0 URL: DOI: https://doi.org/10.1016/j.idm.2023.08.002
| Excerpt / Summary [Infectious Disease Modelling, 11 August 2023]
For many infectious disease outbreaks, the at-risk population changes their behavior in response to the outbreak severity, causing the transmission dynamics to change in real-time. Behavioral change is often ignored in epidemic modeling efforts, making these models less useful than they could be. We address this by introducing a novel class of data-driven epidemic models which characterize and accurately estimate behavioral change. Our proposed model allows time-varying transmission to be captured by the level of “alarm” in the population, with alarm specified as a function of the past epidemic trajectory. We investigate the estimability of the population alarm across a wide range of scenarios, applying both parametric functions and non-parametric functions using splines and Gaussian processes. The model is set in the data-augmented Bayesian framework to allow estimation on partially observed epidemic data. The benefit and utility of the proposed approach is illustrated through applications to data from real epidemics. |
|
|