13.7 Examples & Further reading

  • Summary and best practices by (Skovron and Titiunik 2015) (parts of it in this presentation video)
  • Do Harsher Prison Conditions Reduce Recidivism? (Chen and Shapiro 2007)
    • Treatment: Prison conditions
    • Outcome: Recidivism rates
    • Score: “Upon entry to the federal prison system, an inmate is processed […] individual’s security custody score. The score is intended to predict prisoner misconduct and therefore to measure the supervision needs of individuals.” (Chen and Shapiro 2007, 5)
    • Cutoff: Particular security custody score
  • Racial Profiling and Use of Force in Police Stops: How Local Events Trigger Periods of Increased Discrimination (Legewie 2016)
    • “I argue that racial bias in the use of force increases after relevant events such as the shooting of a police officer by a black suspect. To examine this argument, I design a quasi experiment using data from 3.9 million time and geocoded pedestrian stops in New York City. The findings show that two fatal shootings of police officers by black suspects increased the use of police force against blacks substantially in the days after the shootings. The use of force against whites and Hispanics, however, remained unchanged, and there is no evidence for an effect of two other police murders by a white and Hispanic suspect.”
    • Treatment: Fatal shooting of police officer by black suspect
    • Outcome: Racial bias in the use of force
    • Score: Time
    • Cutoff: Time of the shooting (particular point in time)
  • Politial science: Common application using vote share as score (Q: Cutoff?) and winning election as the treatment (Cuesta and Imai 2016; Lee 2008)
  • Misunderstandings about the Regression Discontinuity Design in the Study of Close Elections (Cuesta and Imai 2016)
    • “While many researchers invoke the local randomization or as-if-random” assumption near the threshold, it tends to be more stringent than the required continuity assumption […] this seemingly subtle point determines the appropriateness of various statistical methods"
  • Evidence on the deleterious impact of sustained use of polynomial regression on causal inference (Gelman and Zelizer 2015)
    • “We recommend that (a) researchers consider the problems which may result from controlling for higher-order polynomials; and […]”

References

Chen, M Keith, and Jesse M Shapiro. 2007. “Do Harsher Prison Conditions Reduce Recidivism? A Discontinuity-Based Approach.” American Law and Economics Review 9 (1): 1–29.

Cuesta, Brandon de la, and Kosuke Imai. 2016. “Misunderstandings About the Regression Discontinuity Design in the Study of Close Elections.” Annual Review of Political Science 19 (1): 375–96.

Gelman, Andrew, and Adam Zelizer. 2015. “Evidence on the Deleterious Impact of Sustained Use of Polynomial Regression on Causal Inference.” Research & Politics 2 (1): 2053168015569830.

Lee, David S. 2008. “Randomized Experiments from Non-Random Selection in U.S. House Elections.” J. Econom. 142 (2): 675–97.

Legewie, Joscha. 2016. “Racial Profiling and Use of Force in Police Stops: How Local Events Trigger Periods of Increased Discrimination.” The American Journal of Sociology 122 (2): 379–424.

Skovron, Christopher, and Rocıo Titiunik. 2015. “A Practical Guide to Regression Discontinuity Designs in Political Science.”