Regression discontinuity I

Readings

• Chapter 6 in Impact Evaluation in Practice (Gertler et al. 2016)
• Chapter 20 in The Effect (Huntington-Klein 2021)

Regression discontinuity

• The example page on regression discontinuity shows how to use R to analyze and estimate causal effects with regression discontinuity

Slides

The slides for today’s lesson are available online as an HTML file. Use the buttons below to open the slides either as an interactive website or as a static PDF (for printing or storing for later). You can also click in the slides below and navigate through them with your left and right arrow keys.

View all slides in new window Download PDF of all slides

Tip

Fun fact: If you type ? (or shift + /) while going through the slides, you can see a list of special slide-specific commands.

Videos

Videos for each section of the lecture are available at this YouTube playlist.

• Introduction
• Arbitrary cutoffs and causal inference
• Drawing lines and measuring gaps
• Main RDD concerns

You can also watch the playlist (and skip around to different sections) here:

In-class stuff

Here are all the materials we’ll use in class:

• Week 10 FAQ slides (PDF)
• Week 10 R code (on Posit.cloud)

Quarto website resources:

• Workshop on creating Quarto websites
• Creating a website
• Bootswatch themes
• Publishing with Posit Cloud Connect (see this too)
• Publishing with Netlify Drop
• Publishing with GitHub Pages

Examples:

• This class website :)
• My website (source)
• Project-specific websites:
  • Navigating Hostility (source)
  • Double RDD with 990 data (source)
  • Pandemic Pass (source)
  • Derogations, Democratic Backsliding, and International Human Rights During the COVID-19 Pandemic (source)
• Interactive illustration website things: https://www.andrewheiss.com/teaching/
• Other websites:
  • 2024 AYS data visualization workshops (source)
  • Workshop on fancy regression (source)
  • ForeignAssistance.gov backup (source)

Other Quarto things

• Citations
  • Complete instructions
  • With RStudio
  • Citation syntax
  • Example of a citation-heavy document (source)
• Cross references
• Layout options
• Callouts
• Interactivity
  • Plotly and ggplotly()
  • Dashboards
  • Observable JS + Observable Plot (like ggplot for Javascript)
  • Examples:
    • Penguin dashboard
    • Book tracker
    • Example book dashboard
    • Interactive maps with OJS

ggplotly() example:

library(tidyverse)
library(plotly)
library(gapminder)

plot_thing <- gapminder |> 
  filter(year == 2007) |> 
  ggplot(aes(x = gdpPercap, y = lifeExp, color = continent)) +
  geom_point(aes(text = country)) +  # text is a special aesthetic for plotly labels
  scale_x_log10()

ggplotly(plot_thing)

OJS example:

NoteR

This is R code!

# Make the gapminder data available to Observable JS
ojs_define(gapminder = gapminder)

NoteObservable

This is NOT R code! This is Observable JS code!

viewof current_year = Inputs.range(
  [1952, 2007], 
  {value: 1952, step: 5, label: "Year:"}
)

// Rotate the data so that it works with OJS
gapminder_js = transpose(gapminder)

// Filter the data based on the selected year
gapminder_filtered = gapminder_js.filter(d => d.year == current_year)

// Plot this thing
Plot.plot({
  x: {type: "log"},
  marks: [
    Plot.dot(gapminder_filtered, {
        x: "gdpPercap", y: "lifeExp", fill: "continent", r: 6,
        channels: {
          Country: d => d.country
        },
        tip: true
      }
    )
  ]}
)

References

Gertler, Paul J., Sebastian Martinez, Patrick Premand, Laura B. Rawlings, and Christel M. J. Vermeersch. 2016. Impact Evaluation in Practice. 2nd ed. Washington, DC: Inter-American Development Bank and World Bank. https://doi.org/10.1596/978-1-4648-0779-4.

Huntington-Klein, Nick. 2021. The Effect: An Introduction to Research Design and Causality. Boca Raton, Florida: Chapman and Hall / CRC. https://theeffectbook.net/.