Description: The large availability of geographically indexed health data, along with advances in computing, have enabled the development of statistical methods for the analysis of spatial epidemiological data. This course will introduce students to the most commonly used statistical models used to understand spatial variation in disease risk.
Learning Objectives: By the end of the course students will be able to:
(i) Recognize different types of spatial data.
(ii) Formulate research questions and determine the appropriate spatial statistical model to analyze the data.
(iii) Understand the concept of spatial correlation and how to estimate it in point-level spatial data.
(iv) Include spatial random effect in generalized linear models for the analysis of spatial data.
(v) Interpret the results of a spatial generalized linear model.
(vi) Perform spatial interpolation of point-referenced data over space to predict missing data at unsampled locations.
(vii) Smooth disease rates and disease counts over space using multilevel hierarchical models.
(viii) Understand the definition of a (disease) cluster.
(ix) Obtain a kernel density estimate of the intensity function representing the likelihood of observing a disease case at a given location.
(x) Identify clusters of disease cases via appropriate statistical methods.
(xi) Formulate statistical models to characterize spatial variation in the distribution of disease cases.
