Upcoming Events

episummer Intensive Meta-Analysis Course Description: Meta-Analysis is the process of synthesizing data from multiple studies to yield a more complete understanding of the effect. It is the core of evidence-based medicine and epidemiology. The goal of this course is to teach students how to perform a meta-analysis, to interpret the results properly, and to present the results in a manner that is clear and intuitive. The techniques that we discuss in these workshops are relevant to any field where a meta-analysis might be employed. Participants typically work in such fields as medicine, epidemiology, health sciences, biostatistics, nursing, veterinary medicine, psychology, education, criminal justice, ecology, marketing, among others. Basic course (20 hours) June 1-15 In the basic course we explain how to conduct and report the results for a meta-analysis. In an analysis where the effect size is consistent across studies the goal will be to identify that common effect size and consider the clinical implications of the findings. In an analysis where the effect size varies across studies the goal will be to identify the mean effect size and also to quantify the variation in effects and consider the clinical implications of this variation: Is it the case that the treatment's effect varies from moderate to large; or from minor to moderate; or is the treatment helpful in some cases but harmful in others? Advanced course (20 hours) June 16-30 In the advanced course we revisit the same datasets we had used in the basic course. Now, rather than simply quantify the heterogeneity in effects, we try to identify factors that may explain that heterogeneity. Specifically, we use subgroup analysis (analogous to ANOVA) to compare the effect size in different sets of studies. And we use meta-regression (analogous to multiple regression) to identify the unique impact of any covariates on the effect size. We also explore other issues in meta-analysis such as publication bias; limitations of the random-effects model; and options for working with a small number of studies. Intensive course (40 hours) June 1-30 The intensive course is simply the basic course plus the advanced course. The basic course runs from June 1-15 and the advanced course runs from June 16-30.

episummer Introduction to Machine Learning for Epidemiologists Course Description This is an introductory course to explore how epidemiologists can use machine learning to advance their research. It consists of 6 modules; each one designed to include approximately 5 hours of material. The first module will provide a general introduction to machine learning and its utility for epidemiologists. The next two modules will introduce a variety of both unsupervised and supervised algorithms, as well as the validation techniques used in various contexts. The following three modules will then focus on specific applications of machine learning within the field of epidemiology, providing clear examples from the scientific literature. Each module will include self-assessments and hands-on programming exercises in R/R Studio to provide practical experience in the application of machine learning for epidemiologic research. Readings and examples will cover multiple substantive areas of epidemiology.

episummer Introduction to Biostatistics Course Description The course will give an overview of the basic tools for the collection, analysis, and presentation of data in all areas of public health. The topics covered will include descriptive statistics; hypothesis testing; methods for comparison of discrete and continuous data including ANOVA, t-test, correlation, chi-squared analysis, linear and logistic regression, and non-parametric approaches. This course will provide a foundation for the skill-building courses and focused epidemiologic courses.  

episummer Spatial Epidemiology Course Description Spatial epidemiology is the study of geographic distributions and determinants of health in populations. The goal of this class is to introduce students to relevant theory and methods, in order to provide the foundational skills required to understand and critically analyze spatial epidemiologic studies. The course emphasizes spatial epidemiology as a sub-discipline of epidemiology while acknowledging the many scientific disciplines that shape it, including biostatistics, cartography, criminology, demography, economics, geography, psychology, and sociology. We begin by defining spatial epidemiology and exploring these multi-disciplinary roots, with particular regard to the theoretical causal mechanisms that provide a bridge between social and physical environmental conditions and population health. We then provide a basic overview of geographic information systems and their utility for descriptive spatial epidemiology—including data visualization and cluster detection—before demonstrating how to incorporate spatial structures within conventional epidemiologic study designs to examine associational and causal relationships between environmental conditions and health outcomes.