2024

Wenn Nord und Süd zusammenarbeiten. Erfahrungen aus einem Projekt in Uganda

Nora Chirikure, and Macartan Humphreys

WZB-Mitteilungen, 2024

Abs

"Die Frage, welche Mechanismen politische Teilhalbe ermöglichen, ist eine der Kernfragen der WZB-Abteilung Institutionen und politische Ungleichheit. Freude und Neugier waren daher groß, als aus der ugandischen Hauptstadt Kampala die Anfrage an das Team um Macartan Humphreys kam, die Erarbeitung einer Bürgercharta zu unterstützen. Es begann ein aufschlussreiches Zusammenspiel von Wissenschaft und Praxis und ein Prozess der Koproduktion von Nord und Süd."
Vermeintlich unpolitisch. Streiks in China folgen anderen Regeln als in nördlichen Industrieländern

Yuequan Guo

WZB-Mitteilungen, 2024

Abs

"Ein Jahr hat Yuequan Guo in Industriebetrieben zweier Provinzen im Osten Chinas verbracht, um zu verstehen, wie Streiks unter den stren- gen Augen von Geschäftsführung und Regierung funktionieren. Die Formen sind andere als in den gut erforschten Industrieländern des Globalen Nordens, es unterscheiden sich Forderungen und Ergebnisse. Es wäre aber voreilig anzunehmen, Streiks schwacher Organisationen im starken Staat seien unpolitisch."
Ungleichgewicht der Macht

Nora Chirikure, and Lennard Naumann

WZB-Mitteilungen, 2024

Abs HTML

"Forschende aus unterschiedlichen Teilen der Erde haben immer noch sehr ungleiche Startchancen. Das gilt für die Finanzierung ihrer Forschung, akademische Karrierewege, für Visa und Netzwerke. Nora Chirikure und Lennard Naumann fragen, was es braucht, damit Süd-Nord-Forschungspartnerschaften wirklich gleichberechtigt sind und Forschung aus dem Globalen Süden Erfolg hat."
Who Wants to be Legible? Digitalization and Intergroup Inequality in Kenya

Lisa Garbe, Nina McMurry, Alexandra Scacco, and 1 more author

Comparative Political Studies, 2024

Abs PDF

"Governments across the Global South have begun introducing biometric IDs (eIDs) in an attempt to improve citizen-state legibility. While such initiatives can improve government efficiency, they also raise important questions about citizen privacy, especially for groups with a history of mistrust in the state. If concerns about increased legibility produce differential eID uptake or changes in political behavior, eID initiatives may exacerbate societal inequalities. In a conjoint experiment with 2,073 respondents from four Kenyan regions, we examine how perceptions of and willingness to register for eID under different policy conditions vary across politically dominant, opposition, and ’securitized’ (heavily policed) ethnic groups. Our results indicate broad support for expanded legibility, with respondents across groups preferring policies that link eIDs with a range of government functions. However, we find meaningful group-level variation in support for specific policy features, and suggestive evidence that policies facilitating greater surveillance may discourage opposition political participation."

2023

A 2 million-person, campaign-wide field experiment shows how digital advertising affects voter turnout

Minali Aggarwal, Jennifer Allen, Alexander Coppock, and 7 more authors

Nature Human Behaviour, 2023
COVID-19 and mental health in 8 low-and middle-income countries: A prospective cohort study

Nursena Aksunger, Corey Vernot, Rebecca Littman, and 8 more authors

PLoS Medicine, 2023
Pulling through elections by pulling the plug: Internet disruptions and electoral violence in Uganda

Lisa Garbe

Journal of Peace Research, 2023
The political power of internet business: A comprehensive dataset of Telecommunications Ownership and Control (TOSCO)

Tina Freyburg, Lisa Garbe, and Véronique Wavre

The Review of International Organizations, 2023
How African countries respond to fake news and hate speech

Lisa Garbe, Lisa-Marie Selvik, and Pauline Lemaire

Information, Communication & Society, 2023
Softening the corrective effect of populism: populist parties’ impact on political interest

Miroslav Nemčok, Constantin Manuel Bosancianu, Olga Leshchenko, and 1 more author

West European Politics, 2023

Trading Liberties: Estimating COVID-19 Policy Preferences from Conjoint Data

Felix Hartmann, Macartan Humphreys, Ferdinand Geissler, and 2 more authors

Political Analysis, 2023

@article{hartmann2023trading,
  title = {Trading Liberties: Estimating COVID-19 Policy Preferences from Conjoint Data},
  author = {Hartmann, Felix and Humphreys, Macartan and Geissler, Ferdinand and Kl{\"u}ver, Heike and Giesecke, Johannes},
  journal = {Political Analysis},
  pages = {1--9},
  year = {2023},
  keywords = {health, experimental, methods},
  pap = {https://osf.io/4vgf6/},
}

CUP
Integrated Inferences: Causal Models for Qualitative and Mixed-Method Research

Macartan Humphreys, and Alan M Jacobs

2023

Abs Bib HTML Code

Integrated Inferences develops a framework for using causal models and Bayesian updating for qualitative and mixed-methods research. By making, updating, and querying causal models, researchers are able to integrate information from different data sources while connecting theory and empirics in a far more systematic and transparent manner than standard qualitative and quantitative approaches allow. This book provides an introduction to fundamental principles of causal inference and Bayesian updating and shows how these tools can be used to implement and justify inferences using within-case (process tracing) evidence, correlational patterns across many cases, or a mix of the two. The authors also demonstrate how causal models can guide research design, informing choices about which cases, observations, and mixes of methods will be most useful for addressing any given question.
@book{humphreysjacobs2023, title = {Integrated Inferences: Causal Models for Qualitative and Mixed-Method Research}, author = {Humphreys, Macartan and Jacobs, Alan M}, year = {2023}, url = {https://www.cambridge.org/core/books/integrated-inferences/45B07964AD4718A74CDE3E35A31F26FA}, publisher = {Cambridge University Press}, keywords = {methods} }
PUP
Research Design in the Social Sciences: Declaration, Diagnosis, and Redesign

Graeme Blair, Alexander Coppock, and Macartan Humphreys

2023

Abs Bib HTML Code

Assessing the properties of research designs before implementing them can be tricky for even the most seasoned researchers. This book provides a powerful framework—Model, Inquiry, Data Strategy, and Answer Strategy, or MIDA—for describing any empirical research design in the social sciences. MIDA enables you to characterize the key analytic features of observational and experimental designs, qualitative and quantitative designs, and descriptive and causal designs. An accompanying algorithm lets you declare designs in the MIDA framework, diagnose properties such as bias and precision, and redesign features like sampling, assignment, measurement, and estimation procedures. Research Design in the Social Sciences is an essential tool kit for the entire life of a research project, from planning and realization of design to the integration of your results into the scientific literature.
@book{blaircoppockhumphreys2023, title = {Research Design in the Social Sciences: Declaration, Diagnosis, and Redesign}, author = {Blair, Graeme and Coppock, Alexander and Humphreys, Macartan}, year = {2023}, url = {https://press.princeton.edu/books/paperback/9780691199573/research-design-in-the-social-sciences}, publisher = {Princeton University Press}, keywords = {methods}, }
WP
Political salience and regime resilience

Sebastian Schweighofer-Kodritsch, Steffen Huck, and Macartan Humphreys

2023

Abs Bib HTML PDF Code

We study a version of a canonical model of attacks against political regimes where agents have an expressive utility for taking political stances that is scaled by the salience of political decision-making. Increases in political salience can have divergent effects on regime stability depending on costs of being on the losing side. When regimes have weak sanctioning mechanisms, middling levels of salience can pose the greatest threat, as regime supporters are insufficiently motivated to act on their preferences and regime opponents are sufficiently motivated to stop conforming. Our results speak to the phenomenon of charged debates about democracy by identifying conditions under which heightened interest in political decision-making can pose a threat to democracy in and of itself.
@unpublished{SchweighoferKodritsch2022, title = {Political salience and regime resilience}, author = {Schweighofer-Kodritsch, Sebastian and Huck, Steffen and Humphreys, Macartan}, year = {2023}, keywords = {democracy, theory}, }

2022

From Recognition to Integration: Indigenous Autonomy, State Authority, and National Identity in the Philippines

Nina McMurry

American Political Science Review, 2022
SMR

Bounding causes of effects with mediators

Philip Dawid, Macartan Humphreys, and Monica Musio

Sociological Methods & Research, 2022

Abs HTML PDF Code

Suppose X and Y are binary exposure and outcome variables, and we have full knowledge of the distribution of Y, given application of X. We are interested in assessing whether an outcome in some case is due to the exposure. This ’probability of causation’ is of interest in comparative historical analysis where scholars use process tracing approaches to learn about causes of outcomes for single units by observing events along a causal path. The probability of causation is typically not identified, but bounds can be placed on it. Here, we provide a full characterization of the bounds that can be achieved in the ideal case that X and Y are connected by a causal chain of complete mediators, and we know the probabilistic structure of the full chain. Our results are largely negative. We show that, even in these very favorable conditions, the gains from positive evidence on mediators is modest.
PLOS
Public support for global vaccine sharing in the COVID-19 pandemic: Evidence from Germany

Ferdinand Geissler, Felix Hartmann, Macartan Humphreys, and 2 more authors

PLOS ONE, 2022

Abs Bib HTML PDF Code

By September 2021 an estimated 32% of the global population was fully vaccinated for COVID-19 but the global distribution of vaccines was extremely unequal, with 72% or more vaccinated in the ten countries with the highest vaccination rates and less than 2% in the ten countries with the lowest vaccination rates. Given that governments need to secure public support for investments in global vaccine sharing, it is important to understand the levels and drivers of public support for international vaccine solidarity. Using a factorial experiment administered to more than 10,000 online survey respondents in Germany in 2021, we demonstrate that the majority of German citizens are against global inequalities in vaccine distribution. Respondents are supportive of substantive funding amounts, on the order of the most generous contributions provided to date, though still below amounts that are likely needed for a successful global campaign. Public preferences appear largely to be driven by intrinsic concern for the welfare of global populations though are in part explained by material considerations—particularly risks of continued health threats from a failure to vaccinate globally. Strategic considerations are of more limited importance in shaping public opinion; in particular we see no evidence for free riding on contributions by other states. Finally, drawing on an additional survey experiment, we show that there is scope to use information campaigns highlighting international health externalities to augment public support for global campaigns.
@article{geissler2022public, title = {Public support for global vaccine sharing in the COVID-19 pandemic: Evidence from Germany}, author = {Geissler, Ferdinand and Hartmann, Felix and Humphreys, Macartan and Kl{\"u}ver, Heike and Giesecke, Johannes}, journal = {PLOS ONE}, volume = {17}, number = {12}, pages = {e0278337}, year = {2022}, publisher = {Public Library of Science}, pap = {https://osf.io/4vgf6/}, keywords = {development, health, experimental} }
WD
Political violence and endogenous growth

Macartan Humphreys

World Development, 2022

Abs Bib HTML PDF Code

I provide an illustration of a dynamic version of Robert Bates’ conjecture that technologies of coercion can be critical to generate prosperity. The model provides support for the conjecture under specified conditions, generates implications for growth paths, including transitions away from coercive strategies, and has implications for the evolution of inequality.
@article{humphreys2022political, title = {Political violence and endogenous growth}, author = {Humphreys, Macartan}, journal = {World Development}, volume = {159}, pages = {105993}, year = {2022}, publisher = {Elsevier}, keywords = {theory, violence, development}, }

2021

Elections and selfishness

Kjetil Bjorvatn, Simon Galle, Lars Ivar Oppedal Berge, and 4 more authors

Electoral Studies, 2021
When Do Strong Parties “Throw the Bums Out”? Competition and Accountability in South African Candidate Nominations

Evan Lieberman, Philip Martin, and Nina McMurry

Studies in Comparative International Development, 2021
Building robust and ethical vaccination verification systems

Baobao Zhang, Laurin Weissinger, Johannes Himmelreich, and 3 more authors

Brookings TechStream, 2021

NatMed

COVID-19 Vaccine Acceptance and Hesitancy in Low- and Middle-Income Countries

Julio S. Solı́s Arce, Shana S. Warren, Niccolò F. Meriggi, and 71 more authors

Nature Medicine, 2021

Abs Bib HTML PDF

Widespread acceptance of COVID-19 vaccines is crucial for achieving sufficient immunization coverage to end the global pandemic, yet few studies have investigated COVID-19 vaccination attitudes in lower-income countries, where large-scale vaccination is just beginning. We analyze COVID-19 vaccine acceptance across 15 survey samples covering 10 low- and middle-income countries (LMICs) in Asia, Africa and South America, Russia (an upper-middle-income country) and the United States, including a total of 44,260 individuals. We find considerably higher willingness to take a COVID-19 vaccine in our LMIC samples (mean 80.3%; median 78%; range 30.1 percentage points) compared with the United States (mean 64.6%) and Russia (mean 30.4%). Vaccine acceptance in LMICs is primarily explained by an interest in personal protection against COVID-19, while concern about side effects is the most common reason for hesitancy. Health workers are the most trusted sources of guidance about COVID-19 vaccines. Evidence from this sample of LMICs suggests that prioritizing vaccine distribution to the Global South should yield high returns in advancing global immunization coverage. Vaccination campaigns should focus on translating the high levels of stated acceptance into actual uptake. Messages highlighting vaccine efficacy and safety, delivered by healthcare workers, could be effective for addressing any remaining hesitancy in the analyzed LMICs.

@article{solis2021covid,
  title = {COVID-19 Vaccine Acceptance and Hesitancy in Low- and Middle-Income Countries},
  author = {Sol{\'\i}s Arce, Julio S. and Warren, Shana S. and Meriggi, Niccolò F. and Scacco, Alexandra and McMurry, Nina and Voors, Maarten and Syunyaev, Georgiy and Malik, Amyn Abdul and Aboutajdine, Samya and Adeojo, Opeyemi and Anigo, Deborah and Armand, Alex and Asad, Saher and Atyera, Martin and Augsburg, Britta and Awasthi, Manisha and Ayesiga, Gloria Eden and Bancalari, Antonella and Nyqvist, Martina Björkman and Borisova, Ekaterina and Bosancianu, Constantin Manuel and García, Magarita Rosa Cabra and Cheema, Ali and Collins, Elliott and Cuccaro, Filippo and Farooqi, Ahsan Zia and Fatima, Tatheer and Fracchia, Mattia and Soria, Mery Len Galindo and Guariso, Andrea and Hasanain, Ali and Jaramillo, Sofía and Kallon, Sellu and Kamwesigye, Anthony and Kharel, Arjun and Kreps, Sarah and Levine, Madison and Littman, Rebecca and Malik, Mohammad and Manirabaruta, Gisele and Mfura, Jean Léodomir Habarimana and Momoh, Fatoma and Mucauque, Alberto and Mussa, Imamo and Nsabimana, Jean Aime and Obara, Isaac and Otálora, María Juliana and Ouédraogo, Béchir Wendemi and Pare, Touba Bakary and Platas, Melina R. and Polanco, Laura and Qureshi, Javaeria Ashraf and Raheem, Mariam and Ramakrishna, Vasudha and Rendrá, Ismail and Shah, Taimur and Shaked, Sarene Eyla and Shapiro, Jacob N. and Svensson, Jakob and Tariq, Ahsan and Tchibozo, Achille Mignondo and Tiwana, Hamid Ali and Trivedi, Bhartendu and Vernot, Corey and Vicente, Pedro C. and Weissinger, Laurin B. and Zafar, Basit and Zhang, Baobao and Karlan, Dean and Callen, Michael and Teachout, Matthieu and Humphreys, Macartan and Mobarak, Ahmed Mushfiq and Omer, Saad B.},
  journal = {Nature Medicine},
  volume = {27},
  number = {8},
  pages = {1385--1394},
  year = {2021},
  publisher = {Nature Publishing Group},
  doi = {https://doi.org/10.1038/s41591-021-01454-y},
  url = {https://www.nature.com/articles/s41591-021-01454-y},
  replication = {https://github.com/wzb-ipi/covid_vaccines_nmed},
  media = {https://nature.altmetric.com/details/109629548},
  status = {published},
  keywords = {health, development}
}

PNAS
Incentives can spur COVID-19 vaccination uptake

Heike Klüver, Felix Hartmann, Macartan Humphreys, and 2 more authors

Proceedings of the National Academy of Sciences, 2021

Abs Bib HTML PDF

Recent evidence suggests that vaccination hesitancy is too high in many countries to sustainably contain COVID-19. Using a factorial survey experiment administered to 20,500 online respondents in Germany, we assess the effectiveness of three strategies to increase vaccine uptake, namely, providing freedoms, financial remuneration, and vaccination at local doctors. Our results suggest that all three strategies can increase vaccination uptake on the order of two to three percentage points (PP) overall and five PP among the undecided. The combined effects could be as high as 13 PP for this group. The returns from different strategies vary across age groups, however, with older cohorts more responsive to local access and younger cohorts most responsive to enhanced freedoms for vaccinated citizens.
@article{kluver2021incentives, title = {Incentives can spur COVID-19 vaccination uptake}, author = {Kl{\"u}ver, Heike and Hartmann, Felix and Humphreys, Macartan and Geissler, Ferdinand and Giesecke, Johannes}, journal = {Proceedings of the National Academy of Sciences}, volume = {118}, number = {36}, pages = {e2109543118}, year = {2021}, publisher = {National Acad Sciences}, doi = {https://doi.org/10.1073/pnas.2109543118}, keywords = {experimental, health}, pap = {https://osf.io/h8rkb/}, replication = {https://wzb-ipi.github.io/covid_hesitancy_2021/} }
SciAdv
Falling living standards during the COVID-19 crisis: Quantitative evidence from nine developing countries

Dennis Egger, Edward Miguel, Shana S. Warren, and 23 more authors

Science advances, 2021

Abs Bib HTML PDF

Despite numerous journalistic accounts, systematic quantitative evidence on economic conditions during the ongoing COVID-19 pandemic remains scarce for most low- and middle-income countries, partly due to limitations of official economic statistics in environments with large informal sectors and subsistence agriculture. We assemble evidence from over 30,000 respondents in 16 original household surveys from nine countries in Africa (Burkina Faso, Ghana, Kenya, Rwanda, Sierra Leone), Asia (Bangladesh, Nepal, Philippines), and Latin America (Colombia). We document declines in employment and income in all settings beginning March 2020. The share of households experiencing an income drop ranges from 8 to 87% (median, 68%). Household coping strategies and government assistance were insufficient to sustain precrisis living standards, resulting in widespread food insecurity and dire economic conditions even 3 months into the crisis. We discuss promising policy responses and speculate about the risk of persistent adverse effects, especially among children and other vulnerable groups.
@article{egger2021falling, title = {Falling living standards during the COVID-19 crisis: Quantitative evidence from nine developing countries}, author = {Egger, Dennis and Miguel, Edward and Warren, Shana S. and Shenoy, Ashish and Collins, Elliott and Karlan, Dean and Parkerson, Doug and Mobarak, A. Mushfiq and Fink, Günther and Udry, Christopher and Walker, Michael and Haushofer, Johannes and Larreboure, Magdalena and Athey, Susan and Lopez-Pena, Paula and Benhachmi, Salim and Humphreys, Macartan and Lowe, Layna and Meriggi, Niccoló F. and Wabwire, Andrew and Davis, C. Austin and Pape, Utz Johann and Graff, Tilman and Voors, Maarten and Nekesa, Carolyn and Vernot, Corey}, journal = {Science advances}, volume = {7}, number = {6}, pages = {eabe0997}, year = {2021}, publisher = {American Association for the Advancement of Science}, doi = {https://doi.org/10.1126/sciadv.abe0997}, keywords = {health, development} }

2020

Does public opinion affect political speech?

Anselm Hager, and Hanno Hilbig

American Journal of Political Science, 2020
WD
The aggregation challenge

Macartan Humphreys, and Alexandra Scacco

World Development, 2020

Abs Bib PDF

Banerjee, Duflo, and Kremer have had an enormous impact on scholarship on the political economy of development. But as RCTs have become more central in this field, political scientists have struggled to draw implications from proliferating micro-level studies for longstanding macro level problems. We describe these challenges and point to recent innovations to help address them.
@article{humphreys2020aggregation, title = {The aggregation challenge}, author = {Humphreys, Macartan and Scacco, Alexandra}, journal = {World Development}, volume = {127}, pages = {104806}, year = {2020}, publisher = {Elsevier}, keywords = {methods, development}, project = {cumulation} }
JOP
Information technology and political engagement: Mixed evidence from Uganda

Guy Grossman, Macartan Humphreys, and Gabriella Sacramone-Lutz

The Journal of Politics, 2020

Abs Bib HTML PDF

This study integrates three related field experiments to learn about how information communications technology (ICT) innovations can affect who communicates with politicians. We implemented a nationwide experiment in Uganda following a smaller-scale framed field experiment that suggested that ICTs can lead to significant “flattening”: marginalized populations used short message service (SMS) based communication at relatively higher rates compared to existing political communication channels. We find no evidence for these effects in the national experiment. Instead, participation rates are extremely low, and marginalized populations engage at especially low rates. We examine possible reasons for these differences between the more controlled and the scaled-up experiments. The evidence suggests that even when citizens have issues they want to raise, technological fixes to communication deficits can be easily undercut by structural weaknesses in political systems.
@article{grossman2020information, title = {Information technology and political engagement: Mixed evidence from Uganda}, author = {Grossman, Guy and Humphreys, Macartan and Sacramone-Lutz, Gabriella}, journal = {The Journal of Politics}, volume = {82}, number = {4}, pages = {1321--1336}, year = {2020}, publisher = {The University of Chicago Press Chicago, IL}, doi = {https://doi.org/10.1086/708339}, keywords = {experimental, development}, project = {sms} }
Chapter
Field experiments, theory, and external validity

Anna Wilke, and Macartan Humphreys

SAGE Handbook of Research Methods in Political Science and International Relations, 2020

Abs Bib HTML PDF Code

Critics of field experiments lament a turn away from theory and criticize findings for weak external validity. In this chapter, we outline strategies to address these challenges. Highlighting the connection between these twin critiques, we discuss how structural approaches can both help design experiments that maximize the researcher’s ability to learn about theories and enable researchers to judge to what extent the results of one experiment can travel to other settings. We illustrate with a simulated analysis of a bargaining problem to show how theory can help make external claims with respect to both populations and treatments and how combining random assignment and theory can both sharpen learning and alert researchers to over-dependence on theory.
@article{wilke2020field, title = {Field experiments, theory, and external validity}, author = {Wilke, Anna and Humphreys, Macartan}, journal = {SAGE Handbook of Research Methods in Political Science and International Relations}, pages = {1007--35}, year = {2020}, publisher = {SAGE London}, keywords = {theory, methods}, project = {cumulation} }
WP
Political and social correlates of covid-19 mortality

Constantin Manuel Bosancianu, Kim Yi Dionne, Hanno Hilbig, and 4 more authors

2020

Abs Bib HTML PDF

What political and social features of states help explain the distribution of reported Covid-19 deaths? We survey existing works on (1) state capacity, (2) political institutions, (3) political priorities, and (4) social structures to identify national-level political and social characteristics that may help explain variation in the ability of societies to limit Covid-19 mortality. Accounting for a simple set of Lasso-chosen controls, we find that measures of interpersonal and institutional trust are persistently associated with reported Covid-19 deaths in theory-consistent directions. Beyond this, however, patterns are poorly predicted by existing theories, and by arguments in the popular press focused on populist governments, women-led governments, and pandemic preparedness. Expert predictions of mortality patterns associated with state capacity, democracy, and inequality, do no better than chance. Overall, our analysis highlights the challenges our discipline’s theories face in accounting for political responses to unanticipated, society-wide crises.
@unpublished{bosancianu2020political, title = {Political and social correlates of covid-19 mortality}, author = {Bosancianu, Constantin Manuel and Dionne, Kim Yi and Hilbig, Hanno and Humphreys, Macartan and Sampada, KC and Lieber, Nils and Scacco, Alexandra Lawrence}, year = {2020}, publisher = {SocArXiv}, url = {https://osf.io/preprints/socarxiv/ub3zd/}, doi = {https://doi.org/10.31235/osf.io/ub3zd}, }

2019

The promise and peril of peacekeeping economies

Bernd Beber, Michael J Gilligan, Jenny Guardado, and 1 more author

International Studies Quarterly, 2019
CUP
Information, accountability, and cumulative learning: Lessons from Metaketa I

Thad Dunning, Guy Grossman, Macartan Humphreys, and 3 more authors

2019

Abs Bib

Throughout the world, voters lack access to information about politicians, government performance, and public services. Efforts to remedy these informational deficits are numerous. Yet do informational campaigns influence voter behavior and increase democratic accountability? Through the first project of the Metaketa Initiative, sponsored by the Evidence in Governance and Politics (EGAP) research network, this book aims to address this substantive question and at the same time introduce a new model for cumulative learning that increases coordination among otherwise independent researcher teams. It presents the overall results (using meta-analysis) from six independently conducted but coordinated field experimental studies, the results from each individual study, and the findings from a related evaluation of whether practitioners utilize this information as expected. It also discusses lessons learned from EGAP’s efforts to coordinate field experiments, increase replication of theoretically important studies across contexts, and increase the external validity of field experimental research.
@book{dunning2019information, title = {Information, accountability, and cumulative learning: Lessons from Metaketa I}, author = {Dunning, Thad and Grossman, Guy and Humphreys, Macartan and Hyde, Susan D and McIntosh, Craig and Nellis, Gareth}, year = {2019}, publisher = {Cambridge University Press}, keywords = {experimental, development}, project = {cumulation} }
SciAdv
Voter information campaigns and political accountability: Cumulative findings from a preregistered meta-analysis of coordinated trials

Thad Dunning, Guy Grossman, Macartan Humphreys, and 8 more authors

Science advances, 2019

Abs Bib HTML PDF

Voters may be unable to hold politicians to account if they lack basic information about their representatives’ performance. Civil society groups and international donors therefore advocate using voter information campaigns to improve democratic accountability. Yet, are these campaigns effective? Limited replication, measurement heterogeneity, and publication biases may undermine the reliability of published research. We implemented a new approach to cumulative learning, coordinating the design of seven randomized controlled trials to be fielded in six countries by independent research teams. Uncommon for multisite trials in the social sciences, we jointly preregistered a meta-analysis of results in advance of seeing the data. We find no evidence overall that typical, nonpartisan voter information campaigns shape voter behavior, although exploratory and subgroup analyses suggest conditions under which informational campaigns could be more effective. Such null estimated effects are too seldom published, yet they can be critical for scientific progress and cumulative, policy-relevant learning.
@article{dunning2019voter, title = {Voter information campaigns and political accountability: Cumulative findings from a preregistered meta-analysis of coordinated trials}, author = {Dunning, Thad and Grossman, Guy and Humphreys, Macartan and Hyde, Susan D and McIntosh, Craig and Nellis, Gareth and Adida, Claire L and Arias, Eric and Bicalho, Clara and Boas, Taylor C and others}, journal = {Science advances}, volume = {5}, number = {7}, pages = {eaaw2612}, year = {2019}, publisher = {American Association for the Advancement of Science}, url = {https://www.science.org/doi/10.1126/sciadv.aaw2612}, doi = {https://doi.org/10.1126/sciadv.aaw2612}, keywords = {experimental, development}, project = {cumulation} }
JDE
Exporting democratic practices: Evidence from a village governance intervention in Eastern Congo

Macartan Humphreys, Raul Sanchez de la Sierra, and Peter Windt

Journal of Development Economics, 2019

Abs Bib HTML PDF

We study a randomized Community Driven Reconstruction (CDR) intervention that provided two years of exposure to democratic practices in 1250 villages in eastern Congo. To assess its impact, we examine behavior in a village-level unconditional cash transfer project that distributed $1000 to 457 treatment and control villages. The unconditonal cash transfer provides opportunities to assess whetherpublic funds get captured, what governance practices are employed by villagers and village elites and whether prior exposure to the CDR intervention alters these behaviors. We find no evidence for such effects. The results cast doubt on current attempts to export democratic practices to local communities.
@article{humphreys2019exporting, title = {Exporting democratic practices: Evidence from a village governance intervention in Eastern Congo}, author = {Humphreys, Macartan and Sierra, Raul Sanchez de la and Van der Windt, Peter}, journal = {Journal of Development Economics}, volume = {140}, pages = {279--301}, year = {2019}, publisher = {Elsevier}, url = {https://www.sciencedirect.com/science/article/abs/pii/S0304387818305078}, doi = {https://doi.org/10.1016/j.jdeveco.2019.03.011}, keywords = {experimental, development}, }
APSR
Declaring and diagnosing research designs

Graeme Blair, Jasper Cooper, Alexander Coppock, and 1 more author

American Political Science Review, 2019

Abs Bib HTML PDF

Researchers need to select high-quality research designs and communicate those designs clearly to readers. Both tasks are difficult. We provide a framework for formally “declaring” the analytically relevant features of a research design in a demonstrably complete manner, with applications to qualitative, quantitative, and mixed methods research. The approach to design declaration we describe requires defining a model of the world (M), an inquiry (I), a data strategy (D), and an answer strategy (A). Declaration of these features in code provides sufficient information for researchers and readers to use Monte Carlo techniques to diagnose properties such as power, bias, accuracy of qualitative causal inferences, and other “diagnosands.” Ex ante declarations can be used to improve designs and facilitate preregistration, analysis, and reconciliation of intended and actual analyses. Ex post declarations are useful for describing, sharing, reanalyzing, and critiquing existing designs. We provide open-source software, DeclareDesign, to implement the proposed approach.
@article{blair2019declaring, title = {Declaring and diagnosing research designs}, author = {Blair, Graeme and Cooper, Jasper and Coppock, Alexander and Humphreys, Macartan}, journal = {American Political Science Review}, volume = {113}, number = {3}, pages = {838--859}, year = {2019}, publisher = {Cambridge University Press}, url = {https://www.cambridge.org/core/journals/american-political-science-review/article/declaring-and-diagnosing-research-designs/3CB0C0BB0810AEF8FF65446B3E2E4926}, doi = {https://doi.org/10.1017/S0003055419000194}, keywords = {methods} }
CPS
Citizen attitudes toward traditional and state authorities: substitutes or complements?

Peter Windt, Macartan Humphreys, Lily Medina, and 2 more authors

Comparative Political Studies, 2019

Abs Bib HTML PDF

Do citizens view state and traditional authorities as substitutes or complements? Past work has been divided on this question. Some scholars point to competition between attitudes toward these entities, suggesting substitution, whereas others highlight positive correlations, suggesting complementarity. Addressing this question, however, is difficult, as it requires assessing the effects of exogenous changes in the latent valuation of one authority on an individual’s support for another. We show that this quantity—a type of elasticity—cannot be inferred from correlations between support for the two forms of authority. We employ a structural model to estimate this elasticity of substitution using data from 816 villages in the Democratic Republic of Congo and plausibly exogenous rainfall and conflict shocks. Despite prima facie evidence for substitution logics, our model’s outcomes are consistent with complementarity; positive changes in citizen valuation of the chief appear to translate into positive changes in support for the government.
@article{van2019citizen, title = {Citizen attitudes toward traditional and state authorities: substitutes or complements?}, author = {Van der Windt, Peter and Humphreys, Macartan and Medina, Lily and Timmons, Jeffrey F and Voors, Maarten}, journal = {Comparative Political Studies}, volume = {52}, number = {12}, pages = {1810--1840}, year = {2019}, publisher = {SAGE Publications Sage CA: Los Angeles, CA}, url = {https://journals.sagepub.com/doi/full/10.1177/0010414018806529?journalCode=cpsa}, doi = {https://doi.org/10.1177/0010414018806529}, keywords = {development} }
JOP
Can the government deter discrimination? Evidence from a randomized intervention in New York City

Albert H Fang, Andrew M Guess, and Macartan Humphreys

The Journal of Politics, 2019

Abs Bib HTML PDF

Racial discrimination persists despite established antidiscrimination laws. A common government strategy to deter discrimination is to publicize the law and communicate potential penalties for violations. We study this strategy by coupling an audit experiment with a randomized intervention involving nearly 700 landlords in New York City and report the first causal estimates of the effect on rental discrimination against blacks and Hispanics of a targeted government messaging campaign. We uncover discrimination levels higher than prior estimates indicate, especially against Hispanics, who are approximately 6 percentage points less likely to receive callbacks and offers than whites. We find suggestive evidence that government messaging can reduce discrimination against Hispanics but not against blacks. The findings confirm discrimination’s persistence and suggest that government messaging can address it in some settings, but more work is needed to understand the conditions under which such appeals are most effective.
@article{fang2019can, title = {Can the government deter discrimination? Evidence from a randomized intervention in New York City}, author = {Fang, Albert H and Guess, Andrew M and Humphreys, Macartan}, journal = {The Journal of Politics}, volume = {81}, number = {1}, pages = {127--141}, year = {2019}, publisher = {University of Chicago Press Chicago, IL}, url = {https://www.journals.uchicago.edu/doi/full/10.1086/700107}, doi = {https://doi.org/10.1086/700107}, keywords = {experimental, identity politics}, project = {housing} }

2018

Can social contact reduce prejudice and discrimination? Evidence from a field experiment in Nigeria

Alexandra Scacco, and Shana S Warren

American Political Science Review, 2018
JDE
Gender quotas in development programming: Null results from a field experiment in Congo

Peter Windt, Macartan Humphreys, and Raul Sanchez Sierra

Journal of Development Economics, 2018

Abs Bib HTML

We examine whether gender quotas introduced by development agencies empower women. As part of a development program, an international organization created community management committees in 661 villages to oversee village level program expenditures. In a randomly selected half of these villages the organization required the committees to have gender parity. Using data on project choice from all participating villages, data on decision making in a later development project (105 villages), and data on citizen attitudes (200 villages), we find no evidence that gender parity requirements empower women. We discuss potential reasons for the null result, including weakness of these social interventions in terms of the engagement they generate, their time horizon, and the weak delegation of responsibilities.
@article{van2018gender, title = {Gender quotas in development programming: Null results from a field experiment in Congo}, author = {Van der Windt, Peter and Humphreys, Macartan and de la Sierra, Raul Sanchez}, journal = {Journal of Development Economics}, volume = {133}, pages = {326--345}, year = {2018}, publisher = {Elsevier}, doi = {https://doi.org/10.1016/j.jdeveco.2018.02.006}, keywords = {development, experimental, identity politics} }
OUP
Why do women co-operate more in women’s groups?

James D Fearon, Macartan Humphreys, and others

Towards Gender Equity in Development, 2018

Abs Bib HTML

We examine a public goods game in 83 communities in northern Liberia. Women contributed substantially more to a small-scale development project when playing with other women than in mixed-gender groups, where they contributed at about the same levels as men. We try to explain this composition effect using a structural model, survey responses, and a second manipulation. Results suggest women in the all-women condition put more weight on co-operation regardless of value of public good, fear of discovery, or desire to match others’ behaviour. Game players may have stronger motivation to signal public-spiritedness when primed to consider themselves representatives of the women of the community.
@article{fearon2018women, title = {Why do women co-operate more in women’s groups?}, author = {Fearon, James D and Humphreys, Macartan and others}, journal = {Towards Gender Equity in Development}, pages = {217}, year = {2018}, publisher = {Oxford Scholarship Online}, url = {https://www.econstor.eu/handle/10419/190008} }

2017

IJE
Commentary: Biases in the assessment of long-run effects of deworming

Macartan Humphreys

International Journal of Epidemiology, 2017

Abs Bib PDF

"Jullien and colleagues provide a critique of three working papers on the long-run effects of deworming interventions. Despite being unpublished, these three papers have been prominent in the public debate in support of calls for such interventions over the past few years. What can we really infer from them?"
@article{humphreys2016commentary, title = {Commentary: Biases in the assessment of long-run effects of deworming}, author = {Humphreys, Macartan}, journal = {International Journal of Epidemiology}, volume = {45}, number = {6}, pages = {2163--2165}, year = {2017}, publisher = {Oxford University Press}, keywords = {health} }

By keyword

vertical linkages

2024

Who Wants to be Legible? Digitalization and Intergroup Inequality in Kenya

Lisa Garbe, Nina McMurry, Alexandra Scacco, and 1 more author

Comparative Political Studies, 2024

Abs PDF

"Governments across the Global South have begun introducing biometric IDs (eIDs) in an attempt to improve citizen-state legibility. While such initiatives can improve government efficiency, they also raise important questions about citizen privacy, especially for groups with a history of mistrust in the state. If concerns about increased legibility produce differential eID uptake or changes in political behavior, eID initiatives may exacerbate societal inequalities. In a conjoint experiment with 2,073 respondents from four Kenyan regions, we examine how perceptions of and willingness to register for eID under different policy conditions vary across politically dominant, opposition, and ’securitized’ (heavily policed) ethnic groups. Our results indicate broad support for expanded legibility, with respondents across groups preferring policies that link eIDs with a range of government functions. However, we find meaningful group-level variation in support for specific policy features, and suggestive evidence that policies facilitating greater surveillance may discourage opposition political participation."

horizontal contestation

exclusion

2023

Pulling through elections by pulling the plug: Internet disruptions and electoral violence in Uganda

Lisa Garbe

Journal of Peace Research, 2023

elite connections

methods

2023

Trading Liberties: Estimating COVID-19 Policy Preferences from Conjoint Data

Felix Hartmann, Macartan Humphreys, Ferdinand Geissler, and 2 more authors

Political Analysis, 2023

Bib HTML PDF Code

@article{hartmann2023trading,
  title = {Trading Liberties: Estimating COVID-19 Policy Preferences from Conjoint Data},
  author = {Hartmann, Felix and Humphreys, Macartan and Geissler, Ferdinand and Kl{\"u}ver, Heike and Giesecke, Johannes},
  journal = {Political Analysis},
  pages = {1--9},
  year = {2023},
  keywords = {health, experimental, methods},
  pap = {https://osf.io/4vgf6/},
}

CUP
Integrated Inferences: Causal Models for Qualitative and Mixed-Method Research

Macartan Humphreys, and Alan M Jacobs

2023

Abs Bib HTML Code

Integrated Inferences develops a framework for using causal models and Bayesian updating for qualitative and mixed-methods research. By making, updating, and querying causal models, researchers are able to integrate information from different data sources while connecting theory and empirics in a far more systematic and transparent manner than standard qualitative and quantitative approaches allow. This book provides an introduction to fundamental principles of causal inference and Bayesian updating and shows how these tools can be used to implement and justify inferences using within-case (process tracing) evidence, correlational patterns across many cases, or a mix of the two. The authors also demonstrate how causal models can guide research design, informing choices about which cases, observations, and mixes of methods will be most useful for addressing any given question.
@book{humphreysjacobs2023, title = {Integrated Inferences: Causal Models for Qualitative and Mixed-Method Research}, author = {Humphreys, Macartan and Jacobs, Alan M}, year = {2023}, url = {https://www.cambridge.org/core/books/integrated-inferences/45B07964AD4718A74CDE3E35A31F26FA}, publisher = {Cambridge University Press}, keywords = {methods} }
PUP
Research Design in the Social Sciences: Declaration, Diagnosis, and Redesign

Graeme Blair, Alexander Coppock, and Macartan Humphreys

2023

Abs Bib HTML Code

Assessing the properties of research designs before implementing them can be tricky for even the most seasoned researchers. This book provides a powerful framework—Model, Inquiry, Data Strategy, and Answer Strategy, or MIDA—for describing any empirical research design in the social sciences. MIDA enables you to characterize the key analytic features of observational and experimental designs, qualitative and quantitative designs, and descriptive and causal designs. An accompanying algorithm lets you declare designs in the MIDA framework, diagnose properties such as bias and precision, and redesign features like sampling, assignment, measurement, and estimation procedures. Research Design in the Social Sciences is an essential tool kit for the entire life of a research project, from planning and realization of design to the integration of your results into the scientific literature.
@book{blaircoppockhumphreys2023, title = {Research Design in the Social Sciences: Declaration, Diagnosis, and Redesign}, author = {Blair, Graeme and Coppock, Alexander and Humphreys, Macartan}, year = {2023}, url = {https://press.princeton.edu/books/paperback/9780691199573/research-design-in-the-social-sciences}, publisher = {Princeton University Press}, keywords = {methods}, }

2022

SMR

Bounding causes of effects with mediators

Philip Dawid, Macartan Humphreys, and Monica Musio

Sociological Methods & Research, 2022

Abs HTML PDF Code

Suppose X and Y are binary exposure and outcome variables, and we have full knowledge of the distribution of Y, given application of X. We are interested in assessing whether an outcome in some case is due to the exposure. This ’probability of causation’ is of interest in comparative historical analysis where scholars use process tracing approaches to learn about causes of outcomes for single units by observing events along a causal path. The probability of causation is typically not identified, but bounds can be placed on it. Here, we provide a full characterization of the bounds that can be achieved in the ideal case that X and Y are connected by a causal chain of complete mediators, and we know the probabilistic structure of the full chain. Our results are largely negative. We show that, even in these very favorable conditions, the gains from positive evidence on mediators is modest.

2020

WD
The aggregation challenge

Macartan Humphreys, and Alexandra Scacco

World Development, 2020

Abs Bib PDF

Banerjee, Duflo, and Kremer have had an enormous impact on scholarship on the political economy of development. But as RCTs have become more central in this field, political scientists have struggled to draw implications from proliferating micro-level studies for longstanding macro level problems. We describe these challenges and point to recent innovations to help address them.
@article{humphreys2020aggregation, title = {The aggregation challenge}, author = {Humphreys, Macartan and Scacco, Alexandra}, journal = {World Development}, volume = {127}, pages = {104806}, year = {2020}, publisher = {Elsevier}, keywords = {methods, development}, project = {cumulation} }
Chapter
Field experiments, theory, and external validity

Anna Wilke, and Macartan Humphreys

SAGE Handbook of Research Methods in Political Science and International Relations, 2020

Abs Bib HTML PDF Code

Critics of field experiments lament a turn away from theory and criticize findings for weak external validity. In this chapter, we outline strategies to address these challenges. Highlighting the connection between these twin critiques, we discuss how structural approaches can both help design experiments that maximize the researcher’s ability to learn about theories and enable researchers to judge to what extent the results of one experiment can travel to other settings. We illustrate with a simulated analysis of a bargaining problem to show how theory can help make external claims with respect to both populations and treatments and how combining random assignment and theory can both sharpen learning and alert researchers to over-dependence on theory.
@article{wilke2020field, title = {Field experiments, theory, and external validity}, author = {Wilke, Anna and Humphreys, Macartan}, journal = {SAGE Handbook of Research Methods in Political Science and International Relations}, pages = {1007--35}, year = {2020}, publisher = {SAGE London}, keywords = {theory, methods}, project = {cumulation} }

2019

APSR
Declaring and diagnosing research designs

Graeme Blair, Jasper Cooper, Alexander Coppock, and 1 more author

American Political Science Review, 2019

Abs Bib HTML PDF

Researchers need to select high-quality research designs and communicate those designs clearly to readers. Both tasks are difficult. We provide a framework for formally “declaring” the analytically relevant features of a research design in a demonstrably complete manner, with applications to qualitative, quantitative, and mixed methods research. The approach to design declaration we describe requires defining a model of the world (M), an inquiry (I), a data strategy (D), and an answer strategy (A). Declaration of these features in code provides sufficient information for researchers and readers to use Monte Carlo techniques to diagnose properties such as power, bias, accuracy of qualitative causal inferences, and other “diagnosands.” Ex ante declarations can be used to improve designs and facilitate preregistration, analysis, and reconciliation of intended and actual analyses. Ex post declarations are useful for describing, sharing, reanalyzing, and critiquing existing designs. We provide open-source software, DeclareDesign, to implement the proposed approach.
@article{blair2019declaring, title = {Declaring and diagnosing research designs}, author = {Blair, Graeme and Cooper, Jasper and Coppock, Alexander and Humphreys, Macartan}, journal = {American Political Science Review}, volume = {113}, number = {3}, pages = {838--859}, year = {2019}, publisher = {Cambridge University Press}, url = {https://www.cambridge.org/core/journals/american-political-science-review/article/declaring-and-diagnosing-research-designs/3CB0C0BB0810AEF8FF65446B3E2E4926}, doi = {https://doi.org/10.1017/S0003055419000194}, keywords = {methods} }

2016

WP
Why a Bayesian researcher might prefer observational data

Macartan Humphreys

2016

Abs Bib PDF

"I give an illustration of a simple problem in which a Bayesian researcher can choose between random assignment of a treatment or delegating assignment to an informed—but motivated—agent. In effect she compares between learning from an RCT or from an observational study. She evaluates designs according to an expected squared error criterion (ESE). I show that for a small problem (n “ 2) if she starts with a prior expectation of no treatment effect but believes that the agent is an advocate of treatment with probability q (and otherwise an opponent) then for all values of q she does at least as well delegating assignment as she does from an RCT and she does strictly better as long as q ≠0.5. For other priors on treatment effects, randomization can dominate delegation or be dominated by it. As n grows the expected errors from an RCT design fall but errors from delegated assignment do not. Although there is always some prior such that a delegated procedure beats randomized assignment, the converse is not true. For a given prior there may be no delegated procedure that trumps an RCT. With uniform priors for example the RCT dominates delegated assignment for all beliefs on agent motivations when n ≥4. "
@unpublished{bayesian2016, title = {Why a Bayesian researcher might prefer observational data}, author = {Humphreys, Macartan}, year = {2016}, keywords = {methods, causal inference} }

2015

APSR
Mixing methods: A Bayesian approach

Macartan Humphreys, and Alan M Jacobs

American Political Science Review, 2015

Abs Bib HTML PDF Code

We develop an approach to multimethod research that generates joint learning from quantitative and qualitative evidence. The framework—Bayesian integration of quantitative and qualitative data (BIQQ)—allows researchers to draw causal inferences from combinations of correlational (cross-case) and process-level (within-case) observations, given prior beliefs about causal effects, assignment propensities, and the informativeness of different kinds of causal-process evidence. In addition to posterior estimates of causal effects, the framework yields updating on the analytical assumptions underlying correlational analysis and process tracing. We illustrate the BIQQ approach with two applications to substantive issues that have received significant quantitative and qualitative treatment in political science: the origins of electoral systems and the causes of civil war. Finally, we demonstrate how the framework can yield guidance on multimethod research design, presenting results on the optimal combinations of qualitative and quantitative data collection under different research conditions.
@article{humphreys2015mixing, title = {Mixing methods: A Bayesian approach}, author = {Humphreys, Macartan and Jacobs, Alan M}, journal = {American Political Science Review}, volume = {109}, number = {4}, pages = {653--673}, year = {2015}, publisher = {Cambridge University Press}, url = {https://www.cambridge.org/core/journals/american-political-science-review/article/mixing-methods-a-bayesian-approach/BB1DFC2FDA3D7F2224F3341042FEA5F4}, doi = {https://doi.org/10.1017/S0003055415000453}, keywords = {methods}, project = {cumulation}, }

Science

Promoting an open research culture

Brian A Nosek, George Alter, George C Banks, and 8 more authors

Science, 2015

Abs Bib HTML

@article{nosek2015promoting,
  title = {Promoting an open research culture},
  author = {Nosek, Brian A and Alter, George and Banks, George C and Borsboom, Denny and Bowman, Sara D and Breckler, Steven J and Buck, Stuart and Chambers, Christopher D and Chin, Gilbert and Christensen, Garret and others},
  journal = {Science},
  volume = {348},
  number = {6242},
  pages = {1422--1425},
  year = {2015},
  publisher = {American Association for the Advancement of Science},
  url = {https://www.science.org/doi/10.1126/science.aab2374},
  doi = {https://doi.org/10.1126/science.aab2374},
  keywords = {methods},
  project = {integrity}
}

JGDev
Reflections on the ethics of social experimentation

Macartan Humphreys

Journal of Globalization and Development, 2015

Abs Bib HTML PDF

Social scientists are increasingly engaging in experimental research projects of importance for public policy in developing areas. While this research holds the possibility of producing major social benefits, it may also involve manipulating populations, often without consent, sometimes with potentially adverse effects, and often in settings with obvious power differentials between researcher and subject. Such research is currently conducted with few clear ethical guidelines. In this paper I discuss research ethics as currently understood in this field, highlighting the limitations of standard procedures and the need for the construction of appropriate ethics, focusing on the problems of determining responsibility for interventions and assessing appropriate forms of consent.
@article{humphreys2015reflections, title = {Reflections on the ethics of social experimentation}, author = {Humphreys, Macartan}, journal = {Journal of Globalization and Development}, volume = {6}, number = {1}, pages = {87--112}, year = {2015}, publisher = {De Gruyter}, doi = {https://doi.org/10.1515/jgd-2014-0016}, keywords = {methods}, project = {integrity} }

2014

Science

Promoting transparency in social science research

Edward Miguel, Colin Camerer, Katherine Casey, and 8 more authors

Science, 2014

Abs Bib HTML

In this article, we survey recent progress toward research transparency in the social sciences and make the case for standards and practices that help realign scholarly incentives with scholarly values. We argue that emergent practices in medical trials provide a useful, but incomplete, model for the social sciences. New initiatives in social science seek to create norms that, in some cases, go beyond what is required of medical trials.

@article{miguel2014promoting,
  title = {Promoting transparency in social science research},
  author = {Miguel, Edward and Camerer, Colin and Casey, Katherine and Cohen, Joshua and Esterling, Kevin M and Gerber, Alan and Glennerster, Rachel and Green, Don P and Humphreys, Macartan and Imbens, Guido and others},
  journal = {Science},
  volume = {343},
  number = {6166},
  pages = {30--31},
  year = {2014},
  publisher = {American Association for the Advancement of Science},
  url = {https://www.science.org/doi/10.1126/science.1245317},
  doi = {DOI: 10.1126/science.1245317},
  keywords = {methods},
  project = {integrity}
}

2013

PA
Fishing, commitment, and communication: A proposal for comprehensive nonbinding research registration

Macartan Humphreys, Raul Sanchez Sierra, and Peter Windt

Political Analysis, 2013

Abs Bib HTML PDF

Social scientists generally enjoy substantial latitude in selecting measures and models for hypothesis testing. Coupled with publication and related biases, this latitude raises the concern that researchers may intentionally or unintentionally select models that yield positive findings, leading to an unreliable body of published research. To combat this “fishing” problem in medical studies, leading journals now require preregistration of designs that emphasize the prior identification of dependent and independent variables. However, we demonstrate here that even with this level of advanced specification, the scope for fishing is considerable when there is latitude over selection of covariates, subgroups, and other elements of an analysis plan. These concerns could be addressed through the use of a form of comprehensive registration. We experiment with such an approach in the context of an ongoing field experiment for which we drafted a complete “mock report” of findings using fake data on treatment assignment. We describe the advantages and disadvantages of this form of registration and propose that a comprehensive but nonbinding approach be adopted as a first step to combat fishing by social scientists. Likely effects of comprehensive but nonbinding registration are discussed, the principal advantage being communication rather than commitment, in particular that it generates a clear distinction between exploratory analyses and genuine tests.
@article{humphreys2013fishing, title = {Fishing, commitment, and communication: A proposal for comprehensive nonbinding research registration}, author = {Humphreys, Macartan and de la Sierra, Raul Sanchez and Van der Windt, Peter}, journal = {Political Analysis}, volume = {21}, number = {1}, pages = {1--20}, year = {2013}, publisher = {Cambridge University Press}, media = {https://cambridge.altmetric.com/details/1175618}, keywords = {experimental, methods}, project = {integrity} }

2009

WP
Bounds on least squares estimates of causal effects in the presence of heterogeneous assignment probabilities

Macartan Humphreys

2009

Abs Bib PDF

In many contexts, treatment assignment probabilities differ across strata or are correlated with some observable third variables. Regression with covariate adjustment is often used to account for these features. It is known however that in the presence of heterogeneous treatment effects this approach does not yield unbiased estimates of average treatment effects. But it is not well known how estimates generated in this way diverge from unbiased estimates of average treatment effects. Here I show that biases can be large, even in large samples. However I also find conditions under which the usual approach provides interpretable estimates and I identify a monotonicity condition that ensures that least squares estimates lie between estimates of the average treatment effects for the treated and the average treatment effects for the controls. The monotonicity condition can be satisfied for example with Roy-type selection and is guaranteed in the two stratum case.
@unpublished{humphreys2009bounds, title = {Bounds on least squares estimates of causal effects in the presence of heterogeneous assignment probabilities}, author = {Humphreys, Macartan}, journal = {Manuscript, Columbia University}, year = {2009}, keywords = {methods, causal inference}, }