An Alternative Approach to Estimating Who is Most Likely to Respond to Changes in Registration Laws

Abstract

Scholars often seek to understand which individuals are most responsive to the change in some treatment. Such work inevitably faces issues of identification. When the dependent variable is binary, the assumption that the largest effect occurs where p = 0.5 is also encountered. I apply Manski's [(1995). Identification problems in the social sciences. Cambridge: Harvard University Press] non-parametric Bounds approach, which relaxes the functional form and distributional assumptions found in traditional models, in an attempt to resolve the long standing debate on which types of individuals are most affected by changes in registration laws. Under the standard assumption that treats the selection of registration laws as exogenous, the results revise the current understanding. By exploring the power of various behavioral assumptions, new insights into the study of policy changes emerge, calling into question some of the assumptions that are standard in the literature.

How Much Is Minnesota Like Wisconsin? Assumptions and Counterfactuals in Causal Inference with Observational Data

“…In those cases, the regression estimator (which estimates ATE) and the DID estimator (which estimates ATT) are not directly comparable. 12 Our estimates are very similar to those in Hanmer (2009).…”

“…EDR significantly reduces the cost of voting by collapsing voting and registration into the same act. EDR is widely credited with increasing turnout (Wolfinger and Rosenstone 1980;Teixeira 1992;Mitchell and Wlezien 1995;Rhine 1995;Highton and Wolfinger 1998;Timpone 1998;Brians andGrofman 1999, 2001;Knack 2001;Hanmer 2007Hanmer , 2009. Based on this empirical evidence, political scientists are often willing to argue in publications such as the New York Times that if all states adopted EDR, turnout would increase nationwide (Just 2011).…”

“…Such a restriction should reduce heterogeneity and potentially reduce bias in the estimates. Hanmer (2009) uses this approach by using Iowa and South Dakota as control states in a DID analysis, but neither state has a large metro area comparable to Milwaukee and Minneapolis-St. Paul. This is important since in the current population survey (CPS) sample, comparing Minnesota and Wisconsin to Iowa and South Dakota is to mostly compare urban voters to rural voters.…”

Causal Inference with Differential Measurement Error: Nonparametric Identification and Sensitivity Analysis

“…3 3 Nonparametric identification analysis is rarely used in the discipline. Exceptions include applications to ecological inference (Duncan and Davis 1953), voter registration laws (Hanmer 2007), and suicide terrorism (Ashworth et al 2008). …”

When Increased Turnout Matters: Simulating the Partisan Impact of Full Turnout in Senate and Gubernatorial Elections

“…While higher turnout in the South after the collapse of the New Deal coalition was later shown to benefit Democrats, evidence suggests that the end of black disenfranchisement in the 1960s is responsible rather than a broadly applicable turnout-partisan dynamic (see Erikson 1995). Regional trends notwithstanding, most recent research has supported DeNardos conclusion that Democrats do not necessarily benefit from higher turnout (Citrin, Schickler, and Sides 2003;Franklin and Grier 1997;Hanmer 2007Hanmer , 2009Highton and Wolfinger 2001;Neiheisel and Burden 2012).…”