This course will expose students from a variety of quantitative backgrounds to study design and analysis strategies for addressing specific hypotheses using the varied sources of behavioral, social, and population health sciences research data, and the analytic tools available for analyzing these data. The purpose of this foundational course is to lay the groundwork to have a framework for conceptualizing experiments and observational studies that rely on big data in behavioral science and population health. The two types of data included are: (1) intensive or voluminous longitudinal data from mHealth, smartphone, and sensor technologies large and (2) large and complex data from internet data sources such as social media and Google search trends. The course features many speakers from Stanford and other institutions who are carrying out cutting edge research using high-dimensional or heterogenous data using innovative methods. Students will have the opportunity to choose a data set from among a variety of data sources, analyze the data and present their findings to the class. Each student will do a final project in an area of their own primary interest; many students are able to substantially develop projects that they subsequently use in their own thesis or dissertation research. Prerequisites: EPI 258/EPI 259 (or equivalent statistics course, please contact instructor for approval). Students must have some experience in statistical programming in SAS or R.
2-3 units · Medical Option (Med-Ltr-CR/NC)
This course will expose students from a variety of quantitative backgrounds to study design and analysis strategies for addressing specific hypotheses using the varied sources of behavioral, social, and population health sciences research data, and the analytic tools available for analyzing these data. The purpose of this foundational course is to lay the groundwork to have a framework for conceptualizing experiments and observational studies that rely on big data in behavioral science and population health. The two types of data included are: (1) intensive or voluminous longitudinal data from mHealth, smartphone, and sensor technologies large and (2) large and complex data from internet data sources such as social media and Google search trends. The course features many speakers from Stanford and other institutions who are carrying out cutting edge research using high-dimensional or heterogenous data using innovative methods. Students will have the opportunity to choose a data set from among a variety of data sources, analyze the data and present their findings to the class. Each student will do a final project in an area of their own primary interest; many students are able to substantially develop projects that they subsequently use in their own thesis or dissertation research. Prerequisites: EPI 258/259 (or equivalent statistics course, please contact instructor for approval). Students must have some experience in statistical programming in SAS or R.
Offered in Spring 2027 at Stanford University.