About

Jacob W Bowers is a professor in the Departments of Political Science and Statistics at the University of Illinois at Urbana-Champaign. His methodological research centers on the design and analysis of both randomized experiments and non-randomized observational studies, aiming to understand human behavior and improve public policy. His substantive research includes studies on COVID vaccination attitudes in the USA, tax behavior and attitudes in Malawi, and perceptions of group relationships in neighborhoods in Canada. Bowers currently serves as the Methods Director for the Evidence in Governance and Politics (EGAP) network and is co-founder and co-director of the Arnold Ventures Criminal Justice Research network. Since 2015, he has worked at the intersection of social and behavioral science, applied statistics of causal inference, and public policy with various organizations including the Office of Evaluation Sciences in the General Services Administration of the US Federal Government (formerly the White House Social and Behavioral Sciences Team), The Policy Lab at Brown University, and as a Research Affiliate and Fellow at the Center for Advanced Study in the Social and Behavioral Sciences. There, he co-founded the Causal Inference for Social Impact Lab with Carrie Cihak and co-founded Research4Impact, an organization connecting researchers and practitioners to improve public policy, governance, and advocacy. Bowers also contributed to the creation of the first Latin American Political Methodology meeting in Santiago, Chile in 2017. His work with EGAP contributed to an online textbook on field experiments titled The Theory and Practice of Field Experiments: An Introduction from the EGAP Learning Days, which has been translated into Spanish and French. He teaches about causal inference and experiments in the EGAP Learning Days in Latin America and in the Escuela de Invierno de Metodods.

Research topics

• Sociology
• Medicine
• Psychology
• Demography
• Social psychology
• Chemistry
• Materials science
• Composite material
• Metallurgy
• Nanotechnology
• Optoelectronics

Selected publications

• Detecting Where Effects Occur by Testing Hypotheses in Order

  arXiv (Cornell University) · 2026-02-24

  articleOpen access1st authorCorresponding

  Experimental evaluations of public policies often randomize a new intervention within many sites or blocks. After a report of an overall result -- statistically significant or not -- the natural question from a policy maker is: \emph{where} did any effects occur? Standard adjustments for multiple testing provide little power to answer this question. In simulations modeled after a 44-block education trial, the Hommel adjustment -- among the most powerful procedures controlling the family-wise error rate (FWER) -- detects effects in only 11\% of truly non-null blocks. We develop a procedure that tests hypotheses top-down through a tree: test the overall null at the root, then groups of blocks, then individual blocks, stopping any branch where the null is not rejected. In the same 44-block design, this approach detects effects in 44\% of non-null blocks -- roughly four times the detection rate. A stopping rule and valid tests at each node suffice for weak FWER control. We show that the strong-sense FWER depends on how rejection probabilities accumulate along paths through the tree. This yields a diagnostic: when power decays fast enough relative to branching, no adjustment is needed; otherwise, an adaptive $α$-adjustment restores control. We apply the method to 25 MDRC education trials and provide an R package, \texttt{manytestsr}.

  PublisherOA PDF

• Detecting Where Effects Occur by Testing Hypotheses in Order

  Open MIND · 2026-02-24

  preprint1st authorCorresponding

  Experimental evaluations of public policies often randomize a new intervention within many sites or blocks. After a report of an overall result -- statistically significant or not -- the natural question from a policy maker is: \emph{where} did any effects occur? Standard adjustments for multiple testing provide little power to answer this question. In simulations modeled after a 44-block education trial, the Hommel adjustment -- among the most powerful procedures controlling the family-wise error rate (FWER) -- detects effects in only 11\% of truly non-null blocks. We develop a procedure that tests hypotheses top-down through a tree: test the overall null at the root, then groups of blocks, then individual blocks, stopping any branch where the null is not rejected. In the same 44-block design, this approach detects effects in 44\% of non-null blocks -- roughly four times the detection rate. A stopping rule and valid tests at each node suffice for weak FWER control. We show that the strong-sense FWER depends on how rejection probabilities accumulate along paths through the tree. This yields a diagnostic: when power decays fast enough relative to branching, no adjustment is needed; otherwise, an adaptive $α$-adjustment restores control. We apply the method to 25 MDRC education trials and provide an R package, \texttt{manytestsr}.

  DOI

• Development of ZnO Buffer Layers for As‐Doped CdSeTe/CdTe Solar Cells with Efficiency Exceeding 20%

  Advanced Materials Technologies · 2025-03-19 · 4 citations

  articleOpen access

  Abstract The front buffer layer plays an important role in CdSeTe/CdTe solar cells and helps achieve high conversion efficiencies. Incorporating ZnO buffer layers in the CdSeTe/CdTe device structure has led to highly efficient and stable solar cells. In this study, the optimization of ZnO buffer layers for CdSeTe/CdTe solar cells is reported. The ZnO films are radio frequency sputter‐deposited on SnO 2 :F coated soda‐lime glass substrates. The substrate temperature for the ZnO deposition is varied from 22 to 500 °C. An efficiency of 20.74% is achieved using ZnO deposited at 100 °C. The ZnO thickness is varied between 40 nm and 75 nm. Following the ZnO depositions, devices were fabricated using First Solar's CdSeTe/CdTe absorber, CdCl 2 treatment, and back contact. The optimal ZnO deposition temperature and thickness is 100 °C and 65 nm, respectively. The STEM‐EDX analysis shows that within the detection limits, chlorine is not detected at the front interface of the devices using ZnO deposited at 22 °C and 100 °C. However, depositing ZnO at 500 °C results in chlorine segregation appearing at the ZnO/CdSeTe boundary. This suggests that chlorine is not needed to passivate the ZnO/CdSeTe interface during the lower temperature depositions. The nanocrystalline ZnO deposited at lower temperatures results in a high‐quality interface.

  PublisherOA PDFDOI

• Public Service Provision and the Virtuous Circle: Evidence from Malawi

  Studies in Comparative International Development · 2025-12-29

  articleOpen access

  Abstract Many governments struggle to obtain the resources they need to govern effectively. In the virtuous circle model of state development, tax revenue allows governments to provide public goods and services to citizens, and citizens comply with taxation when governments provide sufficient levels of goods and services. The model, however, also suggests a vicious version of the circle, where citizens do not pay taxes, governments lack revenue to provide public goods and services, and citizens therefore continue to not pay taxes. Under this suboptimal equilibrium, governments cannot deliver on their governing and service provision mandates. We study whether a shock to public service provision in a major city in Malawi can induce citizens to pay taxes, thereby shifting the relationship between the city and its citizens from a vicious circle to a virtuous circle. With a difference-in-differences-style analysis, we show that households exposed to new government-provided waste collection expressed more trust in and better perceptions of the local government. Most importantly, these households were more likely to make tax payments. We find that this increase in tax payments largely came from people paying more of what they owed rather than from new taxpayers entering the rolls.

  PublisherOA PDFDOI

• Tensions in Knowledge Accumulation Using Coordinated Intervention Experiments to Improve Public Policy

  Oxford University Press eBooks · 2024-06-18

  book-chapter1st authorCorresponding

  Abstract This chapter has two main goals. It introduces and explains the value of coordinated randomized experiments for informing public policymaking with a special focus on international development, and then articulates tensions inherent in these coordinated experiments. It explains why coordination can help build the evidence base for policy innovation by helping funders and policymakers test existing theories of change in ways that facilitate the cumulation of knowledge across studies. It then articulates tensions or trade-offs that reasonable decision-makers might face given choices between coordinated and uncoordinated experiments, and provides some rough guides to help decision-makers navigate those tensions. We write from the perspective of encouraging coordinated experiments and offer practical alternatives that might be easier to implement than extant models for policy-oriented decision-makers.

  PublisherDOI

• A p-value for Process Tracing and other N=1 Studies

  arXiv (Cornell University) · 2023-10-20

  preprintOpen accessSenior author

  We introduce a method for calculating \(p\)-values to test causal hypotheses in qualitative research \emph{a la} process tracing. As in an experiment, our \(p\)-value tells us how often one would make the same or more compelling observations favoring one theory while entertaining a rival theory. We adapt Fisher's (1935) randomization-based urn model to the reality of qualitative researchers, who cannot randomize history, but can make observations about historical processes. Our test includes a method of sensitivity analysis which allows researchers to account for the possibility of observation bias, as well as a framework for representing the varying strenght of individual pieces of evidence, altoguether informing the robustness of qualitative causal inefernce. We provide simulations and replications of previously published work to illustrate how to execute our test using any type of qualitative data about events that took place within one case. This approach adds to the pluralistic turn in the use of probability theory in theory-testing process tracing by offering a simple model with provable conservatism, while relying on few assumptions the consequences of which can be directly assessed.

  PublisherOA PDFDOI

• THE VALUE OF PRE-ANALYSIS

  2023-01-01

  otherSenior author
  PublisherDOI

• Why and How to Use Pre-Analysis Plans

  SSRN Electronic Journal · 2022-01-01

  articleOpen accessSenior author
  PublisherDOI

• The influence of social norms varies with “others” groups: Evidence from COVID-19 vaccination intentions

  Proceedings of the National Academy of Sciences · 2022 · 67 citations

  • Sociology
  • Social psychology
  • Psychology

  = 996) and a matched design that approximates pair-randomized experiments. We find a strong relationship between perceived vaccination social norms and vaccination intentions when controlling for real risk factors (e.g., age), as well as dimensions known to predict COVID-19 preventive behaviors (e.g., trust in scientists). The strength of the relationship declines as the queried social group grows larger and more heterogeneous. The relationship for copartisans is second in magnitude to that of family and friends among Republicans but undetectable for Democrats. Sensitivity analysis shows that these relationships could be explained away only by an unmeasured variable with large effects (odds ratios between 2 and 15) on social norms perceptions and vaccination intentions. In addition, a prediction from the "false consensus" view that intentions cause perceived social norms is not supported. We discuss the implications for public health policy and understanding social norms.

  PublisherOA PDFDOI

• Evidence from a statewide vaccination RCT shows the limits of nudges

  Nature · 2022-04-06 · 68 citations

  letterOpen access
  PublisherOA PDFDOI

Recent grants

• Collaborative Research: Propensity Scores and Randomization-Based Inference, or Modeling Assignment to Treatment Conditions as Manifestly or Latently Random

  NSF · $33k · 2008–2011

Frequent coauthors

• Julia M. Rohrer

  Leipzig University

  16 shared

• Tony H. Grubesic

  University of California, Riverside

  16 shared

• Duncan J. Watts

  University of Pennsylvania

  16 shared

• Aaron Frank

  16 shared

• Jake M. Hofman

  Microsoft (United States)

  16 shared

• Elisa Jayne Bienenstock

  Arizona State University

  16 shared

• Emorie D Beck

  University of California, Davis

  16 shared

• Matthew Salganik

  Princeton University

  16 shared

Labs

• The Causal Inference for Social Impact LabPI

Education

• PhD., Political Science

  University of California, Berkeley

  2003

• B.A., Ethics, Politics and Economics

  Yale University

  1992