Speaker: Andrew Lawson, Ph.D, Professor of Biostatistics in the Division of Biostatistics and Bioinformatics, Department of Public Health Sciences, College of Medicine, MUSC and is an MUSC Distinguished Professor and ASA Fellow. He was previously a Professor of Biostatistics in the Department of Epidemiology & Biostatistics, University of South Carolina, SC. His PhD is from the University of St. Andrews, UK and was in Spatial Statistics.
Title: 'Multivariate spatio-temporal mixture modeling of health risk with environmental stressors'
Short Bio: Dr. Lawson has over 160 journal papers on the subject of spatial epidemiology, spatial statistics and related areas. In addition to a number of book chapters, he is the author of 10 books in areas related to spatial epidemiology and health surveillance. The most recent of these is Lawson, A.B. et al (eds) (2016) Handbook of Spatial Epidemiology. CRC Press, New York, and in 2018 a 3rd edition of Bayesian Disease Mapping; hierarchical modeling in spatial epidemiology CRC Press. As well as associate editorships on a variety of journals, he is an advisor in disease mapping and risk assessment for the World Health Organization (WHO). He is founding editor of the Elsevier journal Spatial and Spatio-temporal Epidemiology. Dr Lawson has delivered many short courses in different locations over the last 15 years on Bayesian Disease Mapping with OpenBUGS and INLA, Spatial Epidemiology and disease Clustering.
Abstract: Disease incidence varies in both space and time. Spatial and temporal variation can provide key pointers to etiological evidence. Multiple disease analysis can shed light on commonalities between diseases both in term of cumulative impact of environmental stressors and in common etiology. Sharing of effects can be a useful tool in joint modeling of multiple diseases. In this talk, I will explore the use of special mixture models for linking the spatio-temporal variation in three cancers observed at county level: oral/pharyngeal (OCPCa), lung and bronchus (LBCa) and melanoma (MCaS). Models that include both spatial and spatio-temporal predictors thought to be important ecological predictors are examined as well as purely random effect models. Some results that could have importance are: joint models for all diseases do not fit all diseases well; predictor models do not in general explain the variation better than pure random effect models; jumps in risk can dramatically affect overall model performance. MCaS appears to be modelled best in isolation, and the talk will finish by the considering the ecological relation between MCaS and sunlight both spatially and in space –time.
Carroll, R., Lawson, A. B., Faes C, Kirby RS, Aregay M, Watjou K. Spatially-dependent Bayesian model selection for disease mapping. Stat Methods Med Res. 2016; 27(1):250-268.
Carroll, R., Lawson, A. B., Faes, C., Kirby, R., Aregay, M.,Watjou, K., (2017) Space-time variation of respiratory cancers in South Carolina: A flexible multivariate mixture modeling approach to risk estimation. Annals of Epidemiology, 27, 42-51
Lawson, A. B., Carroll, R., Faes, C., Kirby, R., Aregay, M.,Watjou, K., (2017) Spatio-temporal Bayesian Model Selection for Disease Mapping Environmetrics, 28, https://doi.org/10.1002/env.2465
Light Lunch will be served.
Thursday, January 17 at 12:00pm to 1:00pm
17 East 102nd Street, 5th Floor West Tower, D5-122