This page contains link to the lectures I give throughout the semester. Clicking the title of the week’s lecture will go to a PDF, embedded in the user’s browser, by default. The bottom left icons link to the Github directory for the lecture (), the R Markdown document for the lecture (), and a PDF, embedded on Github, for the lecture ().

  • (Theory and) Research Design
    tl;dr: Research is a process that does not 'prove.' Theories are evaluated for (in)consistency with predictions. Everything has assumptions. Think of the quantitative research design as you would a spreadsheet.
         
  • Descriptive Statistics
    tl;dr: Understanding the kind of information your variable communicates will condition how you can describe them, and never trust a summary statistic of a variable (or two variables) without looking at them first.
         
  • Probability and Sampling
    tl;dr: There are very important rules of probability and distributions that underpin applied statistics. Here's a handful of those. Also: here's a crash course on the logic of random sampling and central limit theorem.
         
  • Hypothesis Testing
    tl;dr: Applied hypothesis testing reduces to statements about the probability of the test statistic, given some assumed/fixed population parameter. It's not quite the question you're asking, but it's the answer you're getting.
         
  • Bivariate OLS
    tl;dr: In the simple bivariate case, the OLS model is just a modified slope-intercept equation. Even when you extend it forward, it's still that. There are still major assumptions that underpin what you're doing, but try not to overthink it for now.
         
  • Extending the Linear Model: Fixed Effects, Controls, and Interactions
    tl;dr: Multiple regression is just like bivariate regression, but with more independent variables that communicate partial effects. Fixed effects are a misleading name for 'categorical dummy variables'. *Be mindful when interacting things.*
         
  • Linear Model Diagnostics (and What to Do if You Flunk One)
    tl;dr: The linear model and its OLS estimator have assumptions and you should look into them all for every model you run. Let the LINE mnemonic guide you.
         
  • BONUS: Causality and Ethics
    tl;dr: This is a final lecture---cut for time---about 'causality', what are its (strong) implications, and what are some issues associated with this term and research in general. Budget cuts and time restraints mean I can only put this here for you to see. This won't be a lecture.