UM SPH Courses taught by Park, Sung Kyun

EHS675 Data Analysis for Environmental Epidemiology

Winter term(s)
2 Credit Hour(s)
Instructor(s): Park, Sung Kyun
Prerequisites: BIOSTAT 560 and EPID 503 or 600
Description: This course will introduce non-parametric smoothing methods, such as splines, locally weighted polynomial regression (LOESS) and generalized additive models (GAM), and focus on continuous environmental exposure variables. It will also deal with analysis of correlated data, including longitudinal analysis and time-series analysis that are widely used in environmental epidemiology. It will provide an opportunity to analyze actual population data to learn how to model environmental epidemiologic data, and is designed particularly for students who pursue environmental epidemiologic research. The course will consist of lectures and hands-on practices in computer labs, homework assignments and final projects. R, a free software environment for statistical computing and graphics, will be used.
Syllabus for EHS675 (PDF, 31096 bytes, last modified on Tuesday, November 29, 2011)

Winter term(s)
3 Credit Hour(s)
Instructor(s): Aiello, Allison; Mendes de Leon, Carlos; Park, Sung Kyun
Last offered Winter 2013
Prerequisites: EPID 600 or Perm. Instr.
Description: Formulation of study goals, selection of epidemiologic parameters, sampling strategies, questionnaire design and administration, database construction, entry and validation, interpretation of univariate and bivariate results. Student groups design and execute a pilot field study.

Winter term(s)
3 Credit Hour(s)
Instructor(s): Park, Sung Kyun
Last offered Winter 2013
Prerequisites: BIOSTAT 560 and EPID 503 or 600
Description: This course will introduce non-parametric smoothing methods, such as splines, locally weighted polynomial regression (LOESS) and generalized additive models (GAM), and focus on continuous environmental exposure variables. It will also deal with analysis of multi-level data including analyses of longitudinal data and complex sampling data, and time-series analysis that are widely used in environmental epidemiology. The course will cover how to handle limits of detection in environmental exposure data. It will provide an opportunity to analyze actual population data to learn how to model environmental epidemiologic data, and is designed particularly for students who pursue environmental epidemiologic research. The course will consist of lectures and hands-on practices in computer labs, homework assignments and final projects. R, a free software environment for statistical computing and graphics, will be used.
This course is cross-listed with EHS675 in the Environmental Health Sciences department.
Syllabus for EPID675 (PDF, 31096 bytes, last modified on Tuesday, November 29, 2011)