Sequential Monte Carlo for Sampling Balanced and Compact Redistricting Plans

McCartan, Cory; Imai, Kosuke

doi:10.48550/arxiv.2008.06131

Cited by 8 publications

(16 citation statements)

References 27 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Only 0.12% (186 out of 159997) of the plans in the ensemble behave similarly to the enacted plan in that they produce a single election outcome over the seventeen elections considered (between 2016-2020). Moreover, when the statewide vote fractions start strongly favoring either party, the number of officials that would be elected for that party under the enacted map may be systematically smaller than what is projected under plans from our ensemble (See Figures 2,10,11). This effect is consistently seen when disadvantaging the Democratic party; it is only occasionally seen when disadvantaging the Republican party.…”

mentioning

confidence: 70%

“…In particular, our use of the term gerrymandering does not make reference to any concept of proportionality and includes how the spatial distribution of the state's electorate interacts with the redistricting process.Using historic voting data, we compare the Georgia congressional redistricting plan enacted in 2021 with a large collection of randomly generated non-partisan maps 1 (see Section 1.1 for details). Similar methodologies have been employed in various states, including North Carolina [9, 5], Ohio [13], Pennsylvania [10,14], Virginia [3], Maryland [8], and Wisconsin [6]. In each state, the methods are adapted to account for the state's specific redistricting requirements.…”

mentioning

confidence: 99%

See 1 more Smart Citation

Mathematically Quantifying Gerrymandering and the Non-responsiveness of the 2021 Georgia Congressional Districting Plan

Zhao¹,

Hettle²,

Gupta³

et al. 2022

Preprint

View full text Add to dashboard Cite

While gerrymandering has been widely suspected in Georgia for years, it has been difficult to quantify. We understand a plan to be a partisan gerrymander if it produces election results whose outcomes and structures are not typically seen in maps drawn only with non-partisan considerations. In particular, our use of the term gerrymandering does not make reference to any concept of proportionality and includes how the spatial distribution of the state's electorate interacts with the redistricting process.Using historic voting data, we compare the Georgia congressional redistricting plan enacted in 2021 with a large collection of randomly generated non-partisan maps 1 (see Section 1.1 for details). Similar methodologies have been employed in various states, including North Carolina [9, 5], Ohio [13], Pennsylvania [10,14], Virginia [3], Maryland [8], and Wisconsin [6]. In each state, the methods are adapted to account for the state's specific redistricting requirements. We continue these explorations by examining the partisan behavior under Georgia's enacted 2021 congressional map and a collection of maps that were sampled without partisan consideration. Our main findings are as follows:

show abstract

mentioning

confidence: 70%

mentioning

confidence: 99%

Mathematically Quantifying Gerrymandering and the Non-responsiveness of the 2021 Georgia Congressional Districting Plan

Zhao¹,

Hettle²,

Gupta³

et al. 2022

Preprint

View full text Add to dashboard Cite

show abstract

“…It is difficult to construct a tractable probability distribution for districting plans, since the space of plans is discrete and lacks a natural metric structure. Thankfully, in recent years a number of algorithms have been developed which sample districting plans from specific distributions (Fifield et al 2020;DeFord, Duchin, and Solomon 2021;Carter et al 2019;McCartan and Imai 2020). These distributions can generally be characterized as maximum-entropy distributions on the space of all valid districting plans, in combination with several moment constraints.…”

Section: Modeling Districting Plansmentioning

confidence: 99%

Individual and Differential Harm in Redistricting

McCartan¹,

Kenny²

2022

Preprint

Self Cite

View full text Add to dashboard Cite

Social scientists have developed dozens of measures for assessing partisan bias in redistricting. But these measures cannot be easily adapted to other groups, including those defined by race, class, or geography. Nor are they applicable to single- or no-party contexts such as local redistricting. To overcome these limitations, we propose a unified framework of harm for evaluating the impacts of a districting plan on individual voters and the groups to which they belong. We consider a voter harmed if their chosen candidate is not elected under the current plan, but would be under a different plan. Harm improves on existing measures by both focusing on the choices of individual voters and directly incorporating counterfactual plans. We discuss strategies for estimating harm, and demonstrate the utility of our framework through analyses of partisan gerrymandering in New Jersey, voting rights litigation in Alabama, and racial dynamics of Boston City Council elections.

show abstract

“…We examine the fitness-for-use of PPMFs through a variety of redistricting and voting rights analyses. In particular, we employ a set of recently developed simulation methods that can generate a large number of realistic redistricting maps under a set of legal and other relevant constraints, such as contiguity, compactness, population parity, and preservation of communities of interest and counties [4,5,6,7,8,9,10]. These simulation methods have been extensively used by expert witnesses in recent court cases on redistricting, including Common Cause v. Lewis (2020), Rucho v. Elections (2015).…”

Section: June 1 2021mentioning

confidence: 99%

“…In our modal analysis, we simulate realistic district plans under the scenario that population counts are given by each of the three datasets. All simulations were conducted with the SMC redistricting sampler of [9], except for the Louisiana House of Representatives Districts for East Baton Rouge, which were conducted with a Merge-Split-type MCMC sampler similar to that of [5,6]. Both of these sampling algorithms are implemented in the open-source software package redist [10].…”

Section: Overview Of Analysismentioning

confidence: 99%

The Impact of the U.S. Census Disclosure Avoidance System on Redistricting and Voting Rights Analysis

Kenny,

Kuriwaki,

McCartan

et al. 2021

Preprint

Self Cite

View full text Add to dashboard Cite

The US Census Bureau plans to protect the privacy of 2020 Census respondents through its Disclosure Avoidance System (DAS), which attempts to achieve differential privacy guarantees by adding noise to the Census microdata. By applying redistricting simulation and analysis methods to DAS-protected 2010 Census data, we find that the protected data are not of sufficient quality for redistricting purposes. We demonstrate that the injected noise makes it impossible for states to accurately comply with the One Person, One Vote principle. Our analysis finds that the DAS-protected data are biased against certain areas, depending on voter turnout and partisan and racial composition, and that these biases lead to large and unpredictable errors in the analysis of partisan and racial gerrymanders. Finally, we show that the DAS algorithm does not universally protect respondent privacy. Based on the names and addresses of registered voters, we are able to predict their race as accurately using the DAS-protected data as when using the 2010 Census data. Despite this, the DAS-protected data can still inaccurately estimate the number of majority-minority districts. We conclude with recommendations for how the Census Bureau should proceed with privacy protection for the 2020 Census.K eywords Census • Redistricting • BISG • Differential privacy • TopDown algorithm • One Person One Vote * To whom correspondence should be addressed. We thank Ben Fifield and the ACLU for providing precinct-level state legislative assignments and election data for several states, and Bruce Willsie of L2, Inc for providing voterfiles.

show abstract

Sequential Monte Carlo for Sampling Balanced and Compact Redistricting Plans

Cited by 8 publications

References 27 publications

Mathematically Quantifying Gerrymandering and the Non-responsiveness of the 2021 Georgia Congressional Districting Plan

Mathematically Quantifying Gerrymandering and the Non-responsiveness of the 2021 Georgia Congressional Districting Plan

Individual and Differential Harm in Redistricting

The Impact of the U.S. Census Disclosure Avoidance System on Redistricting and Voting Rights Analysis

Contact Info

Product

Resources

About