Causal inference:
Vivalt, E. (2020). “How Much Can We Generalize from Impact Evaluations?”, Journal of the European Economics Association, 18(6): 3045–3089. Online Appendices
Vivalt, E. (2019). “Specification Searching and Significance Inflation Across Time, Methods and Disciplines”, Oxford Bulletin of Economics and Statistics, 81(4): 797–816.
Vivalt, E. (2015). “Heterogeneous Treatment Effects in Impact Evaluation”, American Economic Review, Papers and Proceedings, 105(5): 467–470.
Media coverage of research on this theme:
- The Atlantic: “Make Science More Reliable, Win Cash Prizes”
- Vox: “Don’t teach a man to fish. Just give him the goddamn fish”
- The Washington Post: “The Wonkblog Guide to Holiday Giving”
- Mother Jones: “Most Studies of Social Interventions Are Pretty Worthless”
- Lant Pritchett’s mini-series for the Center for Global Development: “Is Your Impact Evaluation Asking Questions That Matter? A Four Part Smell Test”
- Marginal Revolution: “Everyone in development economics should read this paper”
- 3ie’s blog: “Trends in impact evaluation: Did we ever learn?”
Popular articles, podcasts, blog posts and talks:
- Harvard Business Review: “How to Be a Smart Consumer of Social Science Research”
- 80,000 Hours podcast: “Dr Eva Vivalt’s research suggests social science findings don’t generalize. So evidence-based development – what is it good for?”
- Centre for the Study of African Economies (CSAE) Conference 2018, Closing plenary: “Limits to evidence-based interventions for development”
- Effective Altruism Global: Global Poverty talk
- The Inter-American Development Bank’s blog: “How much do impact evaluations (really) help policymaking?”
- The NYU Development Research Institute’s blog: “5 ways to improve your impact evaluation”
- The World Bank’s Development Impact blog: “What do 600 papers on 20 types of interventions tell us about how much impact evaluations generalize?” and “What isn’t reported in impact evaluations?”
Basic income / cash transfer programs:
OpenResearch’s Basic Income RCT with Alex Bartik, David Broockman, Sarah Miller, and Elizabeth Rhodes (formerly Y Combinator Research)
This is a large project in the U.S. that will test the impact of receiving $1,000/month, unconditionally, for 3 years. Researchers may contact me privately for pre-analysis plans on any of the following 12 topics (some of which may merge but which are currently envisaged as separate papers):
- Employment, work quality, and job search
- Time use
- Income, expenditures, and financial health
- Mental and physical health outcomes
- Cognitive outcomes
- Material wellbeing
- Subjective, psychological, and social wellbeing
- Political and social attitudes
- Children’s outcomes
- Intrahousehold outcomes and intimate partner violence
- Migration and housing outcomes
- Crime
We are also working on a COVID-19-related paper.
The Unclaimed Property Puzzle: Billion Dollar Bills Lying on the Sidewalk (sole PI)
Forecasting and development economics:
DellaVigna, S., Pope, D. and Vivalt, E. (2019). “Predict Science to Improve Science”, Science, 366(6464): 428-429.
DellaVigna, S., Otis, N. and Vivalt, E. (2020). “Forecasting the Results of Experiments: Piloting an Elicitation Strategy”, AEA Papers and Proceedings, 110(5): 75-79.
Social Science Prediction Platform website
The above papers are part of a larger project generously supported by the Alfred P. Sloan Foundation and an anonymous foundation.
Vivalt, E. and Coville, A. (2020). “How Do Policy-Makers Update Their Beliefs?”
Online appendix: Forecasting survey on the Social Science Prediction Platform (with .qsf file)
Vivalt, E. and Coville, A. (2021). “Weighing Results: Which Attributes Matter?”
Vivalt, E. and Coville, A. (2020). “Policy-Makers Consistently Overestimate Program Impacts”
Vivalt, E. and Coville, A. (2019). “The Implications of Variance Neglect for the Formation and Estimation of Subjective Expectations”
Vivalt, E. (2020). “Using Priors in Experimental Design: How Much Are We Leaving on the Table?” in Bédécarrats F., I. Guérin, and F. Roubaud, eds., Randomized Control Trials in the Field of Development: The Gold Standard Revisited. London: Oxford University Press.
Media coverage of research on this theme:
- Ars Technica: “‘I Could’ve Told You That’ Might Have a Useful Role to Play in Science”
- Science Daily: “Were those experiment results really so predictable? These researchers aim to find out”
- Behavioral Scientist: “Solving the Problem of ‘Obviousness’ with Prediction Platforms”
Popular articles, podcasts, blog posts and talks:
- The Conversation: “Predicting Research Results Can Mean Better Science and Better Advice”