Research

Solar geoengineering offers a speculative means to cool the planet by reflecting solar radiation into space. While some research suggests that awareness of solar geoengineering could reduce public support for decarbonization through a moral hazard mechanism, other studies indicate that it could serve as a "clarion call" that motivates further action. Using a pre-registered factorial design, we assess how sharing balanced information on solar geoengineering affects attitudes toward decarbonization policies and climate attitudes among 2,509 US residents. We do not find that solar geoengineering information affects support for decarbonization on average, though it may increase support among initially less supportive subgroups; moreover, this information tends to increase the perception that climate change is a daunting problem that cannot be resolved without decarbonization. Our results suggest that concerns about moral hazard should not discourage research on solar geoengineering—as long as the public encounters realistic messages about solar geoengineering’s role.

In randomized controlled trials, given a fixed research budget and/or a limited number of participants, researchers need to optimize statistical efficiency. To this end, researchers often use stratification. However, conventional practices of stratification are agnostic with respect to the predictive relationship between the covariates and the outcomes, even though it is this predictive relationship that motivates stratification. Such practices thus fail to take advantage of all available information when some data is available for both the outcome and the covariates. This paper introduces an adaptive stratification procedure for running an experiment in batches. The method uses data from earlier batches not just to inform stratification decisions but also to rematch observations across different batches without compromising the validity of inference from a superpopulation perspective. Coupled with post-experiment covariate adjustment, this approach can improve the efficiency of common estimators like the average treatment effect. My simulations demonstrate such gains can be substantial.

Politicians sometimes increase tax credits for green energy to incentivize investment in areas vulnerable to economic decline. Can such place-based policies shift local voters’ support? While advocates argue that economic gains from such incentives can realign political preferences by altering the cost–benefit calculus of local voters, competing mechanisms such as disruptions to local communities and ideological resistance may nullify these effects or even trigger backlash. Focusing on the Energy Community Tax Credit Bonus (ECTCB) under the 2022 Inflation Reduction Act, I use a two-dimensional regression discontinuity design (2RDD) to estimate its impact on the Democratic share of the two-party vote in the 2024 presidential election. The analysis suggests a small negative effect (point estimate: −0.0039; 95% confidence interval: [−0.0078, −0.0002]). These findings contribute new causal evidence to the debate on the electoral effects of place-based climate policies. This paper also makes methodological contributions by improving a recently proposed 2RDD estimator with bagging and bootstrap-based inference and evaluating its performance through Monte Carlo simulations.

Difference-in-differences (DiD) designs for estimating causal effects have grown in popularity throughout political science. It is common for DiD studies report their main results using a "dynamic" or "event study" two-way fixed effects (TWFE) regression. This regression combines estimates of average treatment effects for multiple post-treatment time periods alongside placebo tests of the main identifying assumption: parallel trends. Despite their ubiquity, there is little clear and consistent guidance in the discipline for how researchers should estimate dynamic treatment effects. This paper develops a novel decomposition of the dynamic TWFE regression coefficients in terms of their component 2x2 difference-in-differences comparisons in the style of Goodman-Bacon (2021). We use this decomposition to illustrate how bias can result from the incorrect specification of baseline time periods, the inclusion of units and time periods where all observations are treated, and heterogeneity in the dynamic treatment effects across different treatment timing groups. Our results provide additional intuition for the source of bias due to effect heterogeneity—what Sun and Abraham (2021) term "contamination bias"—by directly characterizing the contaminated 2x2 comparisons. We then provide a common framework for connecting the many proposed “heterogeneity-robust” estimators in the literature, noting that they vary primarily in which 2x2 comparisons they choose to include. Through a replication of three studies published in prominent political science journals, we conclude by showing how attentiveness to baseline selection and specification can alter findings.

Social scientists use survey experiments to study the effect of information on individual attitudes and behaviors. However, such experiments may fail to provide respondents with the information as intended. If the theorized mechanism is correct, noncompliance attenuates results, but noncompliance can also arise if the experiment exposes respondents to unintended information, affecting the substantive interpretation of results. In this note, we propose a diagnostic test and recommendations for treatment design that will help researchers evaluate theoretical mechanisms in survey experiments. This placebo test repurposes treatment-relevant manipulation checks to evaluate responses under control conditions. This approach offers a path toward more robust and more informative survey experiments.