Skills Lab: Using Publicly Available Global Health Data in Epidemiology & Biostatistics

1 unit

This skill lab will provide practical variable operationalization, preliminary descriptive analysis, and analysis protocol writing skills that are relevant for students who are: (1) completing independent research projects (i.e., MPH capstone, research practicum, etc.), (2) seeking a data-driven global health career using complex and nationally representative household surveys, and (3) developing the skills to analyze the major causes of morbidity and mortality in low and middle income countries. Students will learn how to access publicly available global health datasets (i.e., Demographic and Health Surveys) commonly used by data scientists and epidemiologists to inform the policies, programs, and services of national health ministries and international health organizations. Students will then gain mastery of statistical and methodological considerations for handling complex survey data by understanding the principles of multistage sampling and probability. Students will increase confidence in developing pragmatic research questions that can be addressed using publicly available global health datasets and exploring data and statistical issues that require reformulation of research questions: missingness, low cell sizes, skip logic patterns, non-response, etc. The course instructor will systematically guide students through important stages of research question formulation, data access, preliminary data analysis, and descriptive statistics. The final project will be a 5 -page, double spaced, APA-style research analysis protocol consisting of research question and rationale (1 page), dataset description (0.5 page), descriptive statistics table (1 page), feasibility of addressing the research question (0.5 page), variable operationalization (1 page), and analytical plan for further descriptive or inferential statistics (1 page, completing the full analysis is not required). Overall, this course will equip students in independently answering a variety of research questions using publicly available global health datasets.