The following screencasts were designed as short guided introductions for particular statistical concepts. They are probably best used as links in problem sets that students can refer to at their own pace, before they set out to tackle harder, open-ended questions.
All code uses R conforms to the tidyverse style and often uses tidyverse syntax, and uses real dataset that can be loaded on any R environment quickly (e.g. through a package built-in dataset). It is geared towards advanced undergraduates or a masters class where students already have some familiarity with probability and inference.
Installing vs. loading scripts, basic structure and sections of a script, function masking.
Running linear regression, formulas, options to the
ggplot2(putting 1-3 together)
".", model matrix creation.
predictwith the testing dataset, generic functions.
Fixed effects syntax with
lfe::felm, adjusting for clustered errors.
Instrumental variables as an omitted variable problem, using both
lfe::felm packages. Uses the proximity to college dataset by Card (1994).
Visualizing regression discontinuity, estimating coefficients with interactions, polynomials, and local linear regression.
Time series data, long form, plotting time trends, interactions, 2 by 2 difference-in-differences, DID with fixed effects.
Thanks to Oscar Torres-Reyna for the data (http://princeton.edu/~otorres/DID101R.pdf).
Arguments, body, and return statement. Also see the function basics tutorial for background.
Choropleth maps using
sf objects in
ggplot2, merging in other variables into sf dataframes.