Hostname: page-component-7b7567c8c-fvjsw Total loading time: 0 Render date: 2026-11-16T11:07:18.590Z Has data issue: false hasContentIssue false

Partisan Imbalance in Regression Discontinuity Studies Based onElectoral Thresholds

Published online by Cambridge University Press:  09 December 2014

Rights & Permissions [Opens in a new window]

Abstract

Many articles use regression discontinuity designs (RDDs) that exploit thediscontinuity in “close” election outcomes to identify various political andeconomic outcomes of interest. One of the most important types of diagnostictests in an RDD is checking for balance in observable variables within thewindow on either side of the threshold. Finding an imbalance raises concernsthat an unobservable variable may exist that affects whether a case ends upabove or below the threshold and also directly affects the dependentvariable of interest. This article shows that imbalance in RDDs exploitingclose elections are likely to arise even in the absence of any type ofstrategic sorting. Imbalance may arise simply due to variation in theunderlying distribution of partisanship in the electorate acrossconstituencies. Using both simulated and actual election data, the studydemonstrates that the imbalances driven by partisanship can be large inpractice. It then shows that although this causes a bias for the most naiveRDDs, the problem can be corrected with commonly used RDDs such as theinclusion of a local linear control function.

Information

Type
Original Articles
Copyright
Copyright © The European Political Science Association 2014 
Figure 0

Fig. 1Illustration of share of Democratic wins in close elections in Democratic-leaning districts. Note: distribution is normal with mean of 60 percent and standard deviation of 6 percent; window used to define close elections is 2 percent.

Figure 1

Fig. 2Probability of a Democratic win in a close election as a function of Democratic normal vote (μD). Note: standard deviation (sigma) of 9 percent. The relationship is shown for seven definitions of close elections (δ).

Figure 2

Table 1aSimulation Results

Figure 3

Table 1bSimulation Results

Figure 4

Table 1cSimulation Results

Figure 5

Fig. 3Share of wins for Democrats (Republicans) in close elections in Democratic- (Republican-) leaning states as a function of definition of close elections (δ). Note: D=Democratic-leaning states; R=Republican-leaning states.

Figure 6

Table 2aImbalance in Gubernatorial Control in Analysis of Statewide Races, 1876–1945

Figure 7

Table 2bImbalance in Gubernatorial Control in Analysis of Statewide Races, 1946–2010

Figure 8

Table 3aParty Incumbency Advantage in Statewide Races, 1876−1945

Figure 9

Table 3bParty Incumbency Advantage in Statewide Races, 1946–2010

Figure 10

Table A.1aParty Incumbency Advantage in US House Races, 1876–1945

Figure 11

Table A.1bParty Incumbency Advantage in US House Races, 1946–2010