First and foremost, I strive to teach my students how to create knowledge from data. But as is often true for empirical work, data are messy, questions are ill-defined, modeling choices are vast, and translating one’s work for a broader audience is difficult. In short, learning from data is tough and requires repeated practice. To that end, I have created statistics and data science courses that enable students to develop their data problem-solving abilities by iterating through the entire data analysis process.
At Harvard, I taught Stat 100: Introduction to Statistics and Data Science (lecture slides here), a first course in data analysis and statistical thinking, Stat 108: Introduction to Statistical Computing with R (lecture slides here), a second statistics course for students to develop as programmers and to increase their data acumen, and Stat 160: Introduction to Survey Sampling and Estimation, an upper-level course where students learn how to analyze data collected under a complex sampling design. Prior to Harvard, I taught a wide range of courses at Reed College, Swarthmore College, and Whitman College.