How Much Should We Trust Regression Discontinuity Design Estimates? Evidence from Experimental Benchmarks of the Incumbency Advantage

Incumbency Advantage ◽

Previous Election ◽

Us Senate ◽

State Legislative

This paper uses a regression discontinuity design to estimate the degree to which incumbents scare off challengers with previous officeholder experience. The estimates indicate a surprisingly small amount of scare-off, at least in cases where the previous election was nearly tied. As Lee and others have shown (and as we confirm for our samples) the estimated party incumbency advantage in these same cases is quite large—in fact, it is about as large as the average incumbency advantage for all races found using other approaches. Drawing from previous estimates of the electoral value of officeholder experience, we thus calculate that scare-off in these cases accounts for only about 5–7 percent of the party incumbency advantage. We show that these patterns are similar in elections for US House seats, statewide offices and US senate seats, and state legislative seats.

The Effect of Electing Women on Future Female Candidate Selection Patterns: Findings from a Regression Discontinuity Design

Politics & Gender ◽

10.1017/s1743923x19000096 ◽

2019 ◽

Vol 15 (2) ◽

pp. 182-210 ◽

Cited By ~ 1

Author(s):

Michael Jankowski ◽

Kamil Marcinkiewicz ◽

Anna Gwiazda

Keyword(s):

Strong Evidence ◽

Empirical Support ◽

Proportional Representation ◽

Candidate Selection ◽

Contagion Effect ◽

Representation System ◽

Incumbency Advantage ◽

Female Candidate

AbstractIn this article, we address the question of how electing women to national or subnational parliaments affects future female candidate selection in an open-list proportional representation system, using the example of Poland. We consider three potential effects of electing a woman. First, based on existing theories of the incumbency advantage, elected women should have higher chances of reselection and reelection in future elections (incumbency effect). Second, as a result of becoming more powerful within their party, elected women might have a stronger influence on future list composition, and thus more women should run for office on these lists (empowerment effect). Finally, we argue that other parties might adjust their candidate selection patterns in response to the election of women on other party lists (contagion effect). We find strong evidence for the incumbency effect and some support for the contagion effect. The empowerment hypothesis, however, finds no empirical support.

Political Dynasties and the Incumbency Advantage in Party-Centered Environments

American Political Science Review ◽

10.1017/s0003055418000047 ◽

2018 ◽

Vol 112 (3) ◽

pp. 706-712 ◽

Cited By ~ 8

Author(s):

JON H. FIVA ◽

DANIEL M. SMITH

Keyword(s):

United States ◽

Causal Effect ◽

The United States ◽

The Philippines ◽

Organizational Networks ◽

Incumbency Advantage ◽

Level Data

A handful of recent studies have investigated the causal effect of incumbency on dynasty formation in candidate-centered electoral contexts. We use candidate-level data and a regression discontinuity design to estimate the incumbency advantage and its relation to dynasty formation in the party-centered, closed-list, proportional-representation setting of Norway. The results indicate that the incumbency advantage exists even in this party-centered environment; however, in contrast to recent findings for the United States and the Philippines, we find no evidence that incumbency is important to the formation of dynasties. This finding underscores the need for more research into the role of internal party organizational networks in the perpetuation of political dynasties.

A Note on Close Elections and Regression Analysis of the Party Incumbency Advantage

Statistics Politics and Policy ◽

10.1515/spp-2014-0003 ◽

2014 ◽

Vol 5 (1-2) ◽

pp. 1-11

Author(s):

Peter M. Aronow ◽

David R. Mayhew ◽

Winston Lin

Keyword(s):

Regression Analysis ◽

Least Squares ◽

Control Strategy ◽

House Of Representatives ◽

Ordinary Least Squares ◽

Least Squares Regression ◽

Incumbency Advantage ◽

The Us

AbstractMuch research has recently been devoted to understanding the effects of party incumbency following close elections, typically using a regression discontinuity design. Researchers have demonstrated that close elections in the US House of Representatives may systematically favor certain types of candidates, and that a research design that focuses on close elections may therefore be inappropriate for estimation of the incumbency advantage. We demonstrate that any issues raised with the study of close elections may be equally applicable to the ordinary least squares analysis of electoral data, even when the sample contains all elections. When vote share is included as part of a covariate control strategy, the estimate produced by an ordinary least squares regression that includes all elections either exactly reproduces or approximates the regression discontinuity estimate.

A regression discontinuity design analysis of the incumbency advantage and tenure in the U.S. House

Electoral Studies ◽

10.1016/j.electstud.2008.07.010 ◽

2009 ◽

Vol 28 (1) ◽

pp. 123-128 ◽

Cited By ~ 38

Author(s):

Daniel Mark Butler

Keyword(s):

Design Analysis ◽

Incumbency Advantage ◽

The U.S

Personal or Partisan Incumbency Advantage? Evidence from an Electoral Reform at the Local Level in Italy

The B E Journal of Economic Analysis & Policy ◽

10.1515/bejeap-2018-0125 ◽

2019 ◽

Vol 20 (1) ◽

Author(s):

Marco Alberto De Benedetto

Keyword(s):

Local Level ◽

Large Data ◽

Electoral Reform ◽

Incumbency Advantage ◽

Data Set ◽

Term Limit ◽

Municipal Elections ◽

Personal Effect

Abstract We analyze the incumbency advantage using a large data set on Italian municipal elections held from 1993 to 2011. We first apply a non-parametric Sharp Regression Discontinuity Design comparing parties that barely win an election to those that barely lose, exploiting the fact that partisan incumbency status changes discontinuously at the threshold of margin of victory of zero. In order to disentangle the personal incumbency advantage from the partisan effect, we rely on a reform that introduced mayoral term limit, and exploit the exogenous change on the incumbency status of mayors keeping the partisan incumbency status constant. We find that the incumbency advantage is essentially driven by the personal effect. The results are robust to different specifications and estimation strategies with excellent balance in observable characteristics. Also, the effect of interest is larger in magnitude for municipalities located in the South of Italy compared to northern municipalities.