Search

Social scientists use the concept of interactions to study effect dependency. In the causal inference literature, interaction terms may be used in two distinct type of analysis. The first type of analysis focuses on causal interactions, where the analyst is interested in whether two treatments have differing effects when both are administered. The second type of analysis focuses on effect modification, where the analyst investigates whether the effect of a single treatment varies across levels of a baseline covariate. While both forms of interaction analysis are typically conducted using the same type of statistical model, the identification assumptions for these two types of analysis are very different. In this paper, we clarify the difference between these two types of interaction analysis. We demonstrate that this distinction is mostly ignored in the political science literature. We conclude with a review of several applications where we show that the form of the interaction is critical to proper interpretation of empirical results. [ABSTRACT FROM AUTHOR]

Southern states have used a variety of methods to disenfranchise African American voters. Empirical data on the effectiveness of these measures is rare. We present a unique data source from Louisiana that allows us to empirically document voter registration rates from the end of Reconstruction to the present. Using basic time series data, we document how voter registration rates changed over time in response to state restrictions. We then conduct a second analysis, which focuses on Louisiana's use of the Understanding Clause to reduce voter registration among Blacks. We show that in parishes that used the Understanding Clause, Black registration rates dropped by nearly 30 percentage points, with little effect on white registration. The findings of this paper have important implications for understanding the potential for discrimination in the enforcement of modern, ostensibly nonracial, voter eligibility requirements, such as voter ID laws, which grant substantial discretion to local officials in determining voter eligibility. [ABSTRACT FROM AUTHOR]

It is well know that presidents with congressional majorities are better able to implement their legislative agendas. However, it is concluded that presidential attempts influence elections, and hence the findings indicative of presidential influence in previous congressional elections are discussed.

Time series techniques see widespread use in political science. In De Boef and Keele (2008) we outlined a set of statistical methods for stationary data. Those methods have come to be widely used. Grant and Lebo (2015) contend that one of the methods we discussed, the error correction model, should generally not be used with political data. They argue that the error correction model leads to both interpretational and inferential mistakes by applied analysts. While we agree with their statements about equation balance, we show that the error correction model leads to the same inferences as the autoregressive distributed lag model when the data are stationary. We also demonstrate that careful use of an error correction model can help diagnose model misspecification when the equation is unbalanced. Such techniques are useful since pretesting for integration and fractional integration is often a highly uncertain process, which we demonstrate through a simulation exercise. We also highlight two related but often ignored complications in time series: low power and overfitting. We argue that the statistical tests used in time series analyses have little power to detect differences in many of the sample sizes typical in political science. Moreover, given small sample sizes, many analysts overfit their time series models. We argue that the results in the Grant and Lebo replications stem from inadequate sample sizes that make it difficult to conclusively use any time series model. [ABSTRACT FROM AUTHOR]

This issue began as an exchange between Grant and Lebo (2016) and ourselves (Keele, Linn, and Webb 2016) about the utility of the general error correction model (GECM) in political science. The exchange evolved into a debate about Grant and Lebo's proposed alternative to the GECM and the utility of fractional integration methods (FIM). Esarey (2016) and Helgason (2016) weigh in on this part of the debate. Freeman (2016) offers his views on the exchange as well. In the end, the issue leaves readers with a lot to consider. In his comment, Freeman (2016) argues that the exchange has produced little significant progress because of the contributors' failures to consider a wide array of topics not directly related to the GECM or FIM. We are less pessimistic. In what follows, we distill what we believe are the most important elements of the exchange--the importance of balance, the costs and benefits of FIM, and the vagaries of pre-testing. [ABSTRACT FROM AUTHOR]

Many areas of political science focus on causal questions. Evidence from statistical analyses is often used to make the case for causal relationships. While statistical analyses can help establish causal relationships, it can also provide strong evidence of causality where none exists. In this essay, I provide an overview of the statistics of causal inference. Instead of focusing on specific statistical methods, such as matching, I focus more on the assumptions needed to give statistical estimates a causal interpretation. Such assumptions are often referred to as identification assumptions, and these assumptions are critical to any statistical analysis about causal effects. I outline a wide range of identification assumptions and highlight the design-based approach to causal inference. I conclude with an overview of statistical methods that are frequently used for causal inference. [ABSTRACT FROM AUTHOR]

The author discusses the presence or existence of tension among big data, theory and statistics of causal inference. He examine show the focus in causal inference contributes to the confusion about the issue and provides overview of the approach to statistical analysis. The author also explains how the causal inference and the discipline of identification contribute to the development of big data approaches to political science.

Political scientists often turn to natural experiments to draw causal inferences with observational data. Recently, the regression discontinuity design (RD) has become a popular type of natural experiment due to its relatively weak assumptions. We study a special type of regression discontinuity design where the discontinuity in treatment assignment is geographic. In this design, which we call the Geographic Regression Discontinuity (GRD) design, a geographic or administrative boundary splits units into treated and control areas, and analysts make the case that the division into treated and control areas occurs in an as-if random fashion. We show how this design is equivalent to a standard RD with two running variables, but we also clarify several methodological differences that arise in geographical contexts. We also offer a method for estimation of geographically located treatment effects that can also be used to validate the identification assumptions using observable pretreatment characteristics. We illustrate our methodological framework with a re-examination of the effects of political advertisements on voter turnout during a presidential campaign, exploiting the exogenous variation in the volume of presidential ads that is created by media market boundaries. [ABSTRACT FROM PUBLISHER]

Political scientists are often interested in estimating causal effects. Identification of causal estimates with observational data invariably requires strong untestable assumptions. Here, we outline a number of the assumptions used in the extant empirical literature. We argue that these assumptions require careful evaluation within the context of specific applications. To that end, we present an empirical case study on the effect of Election Day Registration (EDR) on turnout. We show how different identification assumptions lead to different answers, and that many of the standard assumptions used are implausible. Specifically, we show that EDR likely had negligible effects in the states of Minnesota and Wisconsin. We conclude with an argument for stronger research designs. [ABSTRACT FROM AUTHOR]

Identifying causal mechanisms is a fundamental goal of social science. Researchers seek to study not only whether one variable affects another but also how such a causal relationship arises. Yet commonly used statistical methods for identifying causal mechanisms rely upon untestable assumptions and are often inappropriate even under those assumptions. Randomizing treatment and intermediate variables is also insufficient. Despite these difficulties, the study of causal mechanisms is too important to abandon. We make three contributions to improve research on causal mechanisms. First, we present a minimum set of assumptions required under standard designs of experimental and observational studies and develop a general algorithm for estimating causal mediation effects. Second, we provide a method for assessing the sensitivity of conclusions to potential violations of a key assumption. Third, we offer alternative research designs for identifying causal mechanisms under weaker assumptions. The proposed approach is illustrated using media framing experiments and incumbency advantage studies. [ABSTRACT FROM PUBLISHER]

The Cox proportional hazards model is widely used to model durations in the social sciences. Although this model allows analysts to forgo choices about the form of the hazard, it demands careful attention to the proportional hazards assumption. To this end, a standard diagnostic method has been developed to test this assumption. I argue that the standard test for nonproportional hazards has been misunderstood in current practice. This test detects a variety of specification errors, and these specification errors must be corrected before one can correctly diagnose nonproportionality. In particular, unmodeled nonlinearity can appear as a violation of the proportional hazard assumption for the Cox model. Using both simulation and empirical examples, I demonstrate how an analyst might be led astray by incorrectly applying the nonproportionality test. [ABSTRACT FROM PUBLISHER]

A correction to an article by Luke Keele, Suzanna Linn, and Clayton McLaughlin which appeared in the 2016 issue of the "Political Analysis" journal is presented.