Applied Biostatistics and Public Health Data Science
New health studies appear in the news every day. But how do we know if the latest drug or intervention actually has merit? Offering crucial tools for evaluating the significance or impact of public health research and interventions, biostatistics is the key.
With demand for biostatisticians far exceeding supply, current and future public health research is at risk. The Certificate in Applied Biostatistics seeks to address this shortage by offering specialized interdisciplinary training in biostatistics to MPH students from other disciplines.
Graduates learn to interpret research results and convey them in clear written and oral presentations suitable for non-expert audiences—a necessary skill for translating science into action. This program augments a graduate’s discipline and opens new professional opportunities, such as serving as a statistical consultant or as a technical resource person in field and programmatic studies.
Applied Biostatistics and Public Health Data Science is open to Columbia MPH students in:
- Environmental Health Sciences
- Health Policy & Management
- Population & Family Health
- Sociomedical Sciences
Applicants should have one semester of calculus with a B+ minimum grade or college credit for AP Calculus. Due to course requirements, the certificate is most compatible for students in Environmental Health Sciences, Epidemiology, and Population & Family Health.
Students who do not meet the Calculus and GRE requirements can be considered based on their Quantitative results from the Fall semester of the Core (Research Methods and Applications studio). For additional information regarding expectations, please contact the Certificate Faculty Lead before requesting enrollment.
The Competencies for this Certificate are as follows:
- Analyze continuous response data using linear regression techniques, including model diagnostics and variable selection.
- Analyze binary response data using table methods and logistic regression models.
- Analyze survival data using Kaplan-Meier curves and Cox Proportional-Hazards models.
- Analyze repeated measures data using generalized estimating equations and mixed models.
- Implement advanced techniques using statistical software, such as SAS or R, to prepare written and oral presentations for non-biostatisticians.
Visit the Certificates Database to learn more about core and credit requirements.
Categorical Data Analysis
This course is a comprehensive overview of methods of analysis for binary and other discrete response data, with applications to epidemiological and clinical studies. Topics discussed include 2×2 tables, m×2 tables, tests of independence, measures of association, power and sample size determination, stratification and matching in design and analysis, interrater agreement, and logistic regression analysis.
Applied Regression II
This course introduces the statistical methods for analyzing censored data, non-normally distributed response data, and repeated measurements data that are commonly encountered in medical and public health research. Topics include estimation and comparison of survival curves, regression models for survival data, logit models, log-linear models, and generalized estimating equations. Examples are drawn from the health sciences.