This is a proposal to develop statistical methods that deal with real-world complexities that commonly arisewhen mapping aggregated disease count data collected for administrative areas.
The specific aims aremotivated by problems encountered in epidemiological studies designed for studying and monitoring healthdisparities, though they are also relevant for area-based studies of environmental effects. Our proposedmethods address issues associated with administrative boundaries changing over time, sparse diseasecounts, spatial confounding, and the heavy computational burdens associated with the analysis of large datasets.
Specific aims of the project are to develop, evaluate, and implement 1) methods for handling boundarymisalignment over time in disease mapping settings, (2) spatial regression models for area-specific diseasecount data exhibiting complex distribution patterns, (3) a theoretical framework and practical diagnosticstrategies for assessing and minimizing bias from spatial confounding, (4) fast, memory-efficient algorithmsfor fitting standard spatio-temporal regression models, (5) efficient user-friendly algorithms and statisticalsoftware that implement these methods with the goal of disseminating them to health science researchers.The proposed methods will be applied to area-specific disease count data on U.S. breast cancer incidence,Boston-area premature mortality, Australian ischemic heart disease rates, and incidence and mortality datafrom the National Cancer Institute's Surveillance, Epidemiology, and End Results (SEER) database. Themethods will allow researchers to better estimate how rates of cancer and other outcomes varygeographically and over time, thereby aiding in the documentation, analysis, and ultimate reduction of healthdisparities in the United States, as defined as one of the overarching goals of Healthy People 2010 (USDepartment of Health and Human Services 2000). This project (Project 1) integrates very closely with thespatial surveillance Project 2: whereas Project 1 focuses on spatio-temporal modeling for the purpose ofcharacterizing the impact of area-based measures of socioeconomic status or other demographiccharacteristics on cancer and other diseases, Project 2 focuses on identifying areas where disease rates areunusually high. Analysis of SEER data features prominently in both Projects 1 and 2. Projects 1 and 3share the common theme of analyzing high-dimensional observational data on cancer. This project reliesheavily on the Statistical Computing Core and will benefit from the organizational infrastructure, teambuilding strategies, short-courses and visitor program provided through the Administrative Core.
Showing the most recent 10 out of 192 publications
