Can Close Election Regression Discontinuity Designs Identify Effects of Winning Politician Characteristics?

Abstract

Politician characteristic regression discontinuity (PCRD) designs leveraging close elections are widely used to isolate effects of an elected politician characteristic on downstream outcomes. Unlike standard regression discontinuity designs, treatment is defined by a predetermined characteristic that could affect a politician's victory margin. I prove that, by conditioning on politicians who win close elections, PCRD estimators identify the effect of the specific characteristic of interest and all compensating differentials—candidate‐level characteristics that ensure elections remain close between candidates who differ in the characteristic of interest. Avoiding this asymptotic bias generally requires assuming either that the characteristic of interest does not affect candidate vote shares or that no compensating differential affects the outcome. Because theories of voting behavior suggest that neither strong assumption usually holds, I further analyze the implications for interpreting continuity tests and consider if and how covariate adjustment, bounding, and recharacterizing treatment can mitigate the posttreatment bias afflicting PCRD designs.

A Costly Commitment: Populism, Economic Performance, and the Quality of Bureaucracy

“…In most cases, this interpretation is sensible, for causal claims about fixed characteristics like populism, gender, and race should be operationalized as a “bundle of sticks” (Hall 2015; Sen and Wasow 2016). However, detecting meaningful discontinuities in candidate‐level characteristics that are conceptually different from populism can help characterize the compound nature of treatment (Marshall 2022).…”

“…We intentionally define τ as the LATE of electing a populist candidate, instead of the LATE of populism alone. In fact, because close elections do not randomly assign candidate characteristics, the RD estimator will recover the effect of the populist attribute of mayors plus all other individual‐ and municipality‐level characteristics that distinguish populist from non‐populist and that allow the former to remain in close election (Marshall 2022). In the following section, we describe how balance tests for mayor‐level characteristics can help us characterize the compound nature of the estimand, as recommended by recent methodological literature (Marshall 2022).…”

The Violence of Law-and-Order Politics: The Case of Law Enforcement Candidates in Brazil

“…Second, if law-and-order candidates have specific attributes that make them more likely to appear in close elections, the local average treatment effect (LATE) might be biased (Marshall 2022). However, and contrary to single-member plurality races, the OLPR system makes it plausible that compensating differentials of law-and-order candidates do not strongly affect their vote shares, an assumption that, if 19 Homicides receive ICD-10 codes ranging between X85-99 and Y00-09; undetermined external causes, which is when the coroner cannot determine intent, receive Y10-34 codes.…”

Do Educated Leaders Affect Economic Development? Evidence from India

“…Following a related argument ofMarshall (2022), it is possible that our RDD identifies the effect of leader's education and all compensating differentials -candidate level characteristics that ensure elections remain close between graduate and non-graduate candidates.…”