Recent research has questioned the value of statistical learning methods for producing accurate predictions in the criminal justice context. Using results from respondents on Amazon Mechanical Turk (MTurkers) who were asked to predict recidivism, Dressel and Farid (2018) argue that nonexperts can achieve predictive accuracy and fairness on par with algorithmic approaches that employ statistical learning models. Analyzing the same data from the original study, this comment employs additional techniques and compares the quality of the predicted probabilities output from statistical learning procedures versus the MTurkers’ evaluations. The metrics presented indicate that statistical approaches do, in fact, outperform the nonexperts in important ways. Based on these new analyses, it is difficult to accept the conclusion presented in Dressel and Farid (2018) that their results “cast significant doubt on the entire effort of algorithmic recidivism prediction.”

Experiments often include multiple treatments, with the primary goal to compare the causal effects of those treatments. This study focuses on comparing the causal anatomies of multiple treatments through the use of causal mediation analysis. It proposes a novel set of comparative causal mediation (CCM) estimands that compare the mediation effects of different treatments via a common mediator. Further, it derives the properties of a set of estimators for the CCM estimands and shows these estimators to be consistent (or conservative) under assumptions that do not require the absence of unobserved confounding of the mediator–outcome relationship, which is a strong and nonrefutable assumption that must typically be made for consistent estimation of individual causal mediation effects. To illustrate the method, the study presents an original application investigating whether and how the international legal status of a foreign policy commitment can increase the domestic political “audience costs” that democratic governments suffer for violating such a commitment. The results provide novel evidence that international legalization can enhance audience costs via multiple causal channels, including by amplifying the perceived immorality of violating the commitment.

This study introduces a new approach to power analysis in the context of estimating a local average treatment effect (LATE), where the study subjects exhibit noncompliance with treatment assignment. As a result of distributional complications in the LATE context, compared to the simple ATE context, there is currently no standard method of power analysis for the LATE. Moreover, existing methods and commonly used substitutes - which include instrumental variable (IV), intent-to-treat (ITT), and scaled ATE power analyses - require specifying generally unknown variance terms and/or rely upon strong and unrealistic assumptions, thus providing unreliable guidance on the power of tests of the LATE. This study develops a new approach that uses standardized effect sizes to place bounds on the power for the most commonly used estimator of the LATE, the Wald IV estimator, whereby variance terms and distributional parameters need not be specified nor assumed. Instead, in addition to the effect size, sample size, and error tolerance parameters, the only other parameter that must be specified by the researcher is the compliance rate. Additional conditions can also be introduced to further narrow the bounds on the power calculation. The result is a generalized approach to power analysis in the LATE context that is simple to implement.

AbstractWe introduce a constrained priority mechanism that combines outcome-based matching from machine learning with preference-based allocation schemes common in market design. Using real-world data, we illustrate how our mechanism could be applied to the assignment of refugee families to host country locations, and kindergarteners to schools. Our mechanism allows a planner to first specify a threshold $\bar g$ for the minimum acceptable average outcome score that should be achieved by the assignment. In the refugee matching context, this score corresponds to the probability of employment, whereas in the student assignment context, it corresponds to standardized test scores. The mechanism is a priority mechanism that considers both outcomes and preferences by assigning agents (refugee families and students) based on their preferences, but subject to meeting the planner’s specified threshold. The mechanism is both strategy-proof and constrained efficient in that it always generates a matching that is not Pareto dominated by any other matching that respects the planner’s threshold.

Protracted global conflicts during the past decade have led to repeated major humanitarian protection crises in Europe. During the height of the Syrian refugee crisis at the end of 2015, Europe hosted around 2.3 million people requesting asylum¹. Today, the ongoing war in Ukraine has resulted in one of the largest humanitarian emergencies in Europe since World War II, with more than eight million Ukrainians seeking refuge across Europe². Here we explore whether repeated humanitarian crises threaten to exhaust solidarity and whether Europeans welcome Ukrainian asylum seekers over other asylum seekers^3,4. We conducted repeat conjoint experiments during the 2015-2016 and 2022 refugee crises, asking 33,000 citizens in 15 European countries to evaluate randomly varied profiles of asylum seekers. We find that public preferences for asylum seekers with specific attributes have remained remarkably stable and general support has, if anything, increased slightly over time. Ukrainian asylum seekers were welcomed in 2022, with their demographic, religious and displacement profile having a larger role than their nationality. Yet, this welcome did not come at the expense of support for other marginalized refugee groups, such as Muslim refugees. These findings have implications for our theoretical understanding of the drivers and resilience of public attitudes towards refugees and for policymakers tasked to find effective responses to the enduring stress on the asylum system^5-8.

What types of asylum seekers are Europeans willing to accept? We conducted a conjoint experiment asking 18,000 eligible voters in 15 European countries to evaluate 180,000 profiles of asylum seekers that randomly varied on nine attributes. Asylum seekers who have higher employability, have more consistent asylum testimonies and severe vulnerabilities, and are Christian rather than Muslim received the greatest public support. These results suggest that public preferences over asylum seekers are shaped by sociotropic evaluations of their potential economic contributions, humanitarian concerns about the deservingness of their claims, and anti-Muslim bias. These preferences are similar across respondents of different ages, education levels, incomes, and political ideologies, as well as across the surveyed countries. This public consensus on what types of asylum seekers to accept has important implications for theory and policy.

Abstract: An ongoing debate in American politics concerns the extent to which subnational politics has become “nationalized.” We advance this debate by collecting issue‐position data on four distinct policy topics from unprecedented national surveys of public officials at both the local and state levels. We then combine this survey data with precinct‐level presidential vote‐share data that is tabulated to match the boundary of each survey respondent's government jurisdiction. In doing so, we demonstrate that national party sorting of subnational officials is substantively and statistically significant across a range of issues with national salience, that it is consistent across local and state levels of government and it cannot be explained by the party sorting of constituents. These findings have implications both for the scope of nationalization as well as its implications for substantive representation.

The effects of austerity in response to financial crises are widely contested and assumed to cause significant electoral backlash. Nonetheless, governments routinely adopt austerity when confronting economic downturns and swelling deficits. We explore this puzzle by distinguishing public acceptance of austerity as a general approach and support for specific austerity packages. Using original survey data from five European countries, we show that austerity is in fact the preferred response among most voters. We develop potential explanations for this surprising preference and demonstrate the empirical limitations of accounts centered on economic interests or an intuitive framing advantage. Instead, we show that the preference for austerity is highly sensitive to its political backers and precise composition of spending cuts and tax hikes. Using a novel approach to estimate support for historical austerity programs, we contend that governments’ strategic crafting of policy packages is a key factor underlying the support for austerity.

In recent years, political and social scientists have made increasing use of conjoint survey designs to study decision-making. Here, we study a consequential question which researchers confront when implementing conjoint designs: How many choice tasks can respondents perform before survey satisficing degrades response quality? To answer the question, we run a set of experiments where respondents are asked to complete as many as 30 conjoint tasks. Experiments conducted through Amazon’s Mechanical Turk and Survey Sampling International demonstrate the surprising robustness of conjoint designs, as there are detectable but quite limited increases in survey satisficing as the number of tasks increases. Our evidence suggests that in similar study contexts researchers can assign dozens of tasks without substantial declines in response quality.