nep-exp New Economics Papers
on Experimental Economics
Issue of 2024‒01‒29
twenty-one papers chosen by



  1. With or without him? Experimental evidence on cash grants and gender-sensitive trainings in Tunisia By Jules Gazeaud; Nausheen Khan; Eric Mvukiyehe; Olivier Sterck
  2. Should Individuals Choose their Own Incentives? Evidence from a Mindfulness Meditation Intervention By Andrej Woerner; Giorgia Romagnoli; Birgit M. Probst; Nina Bartmann; Jonathan N. Cloughesy; Jan Willem Lindemans
  3. Principal’s distributive preferences and the incentivization of agents By Sophie Cêtre; Max Lobeck
  4. Optimistic Framing Increases Responsible Investment of Investment Professionals By Daugaard, Dan; Kent, Danielle; Servátka, Maroš; Zhang, Le
  5. Personal Lies By Gary Charness; Ismael Rodriguez-Lara
  6. Overcoming Time Inconsistency with a Matched Bet: Theory and Evidence from Exercising By Andrej Woerner
  7. Lifetime Memories of Inflation: Evidence from Surveys and the Lab By Salle, Isabelle; Gorodnichenko, Yuriy; Coibion, Olivier
  8. Breaking the Silence: Group Discussions, and the Adoption of Welfare-Improving Technologies By Silvia Castro; Clarissa Mang
  9. Promotions and Group Identity By Ďuriník, Michal; Morita, Hodaka; Servátka, Maroš; Zhang, Le
  10. Jobseekers’ Beliefs about Comparative Advantage and (Mis)Directed Search By Andrea Kiss; Robert Garlick; Kate Orkin; Luke Hensel
  11. Do Pre-Registration and Pre-Analysis Plans Reduce p-Hacking and Publication Bias?: Evidence from 15, 992 Test Statistics and Suggestions for Improvement By Brodeur, Abel; Cook, Nikolai M.; Hartley, Jonathan S.; Heyes, Anthony
  12. Nonspeculative Bubbles Revisited By Steven Tucker; Yilong Xu
  13. Motivations to speculate are the driving forces in experimental asset market bubbles By Steven Tucker; Yilong Xu
  14. Nothing Really Matters: Evaluating Demand-Side Moderators of Age Discrimination in Hiring By Dalle, Axana; Lippens, Louis; Baert, Stijn
  15. Minimum Wages and Racial Discrimination in Hiring: Evidence from a Field Experiment By Alec Brandon; Justin E. Holz; Andrew Simon; Haruka Uchida
  16. Uncertainty about Carbon Impact and the Willingness to Avoid CO2 Emissions By Davide Pace; Taisuke Imai; Peter Schwardmann; Joel van der Weele
  17. Valuing Open Defecation Free Surroundings: Experimental Evidence from a Norm-Based Intervention in India By Sania Ashraf; Cristina Bicchieri; Upasak Das. Alex Shpenev
  18. Inequality of Opportunity and Income Redistribution By Marcel Preuss; Germán Reyes; Jason Somerville; Joy Wu
  19. Do risk, time and prosocial preferences predict risky sexual behaviour of youths in a low-income, high-risk setting? By Thomas, Ranjeeta; Galizzi, Matteo M.; Moorhouse, Louisa; Nyamukapa, Constance; Hallett, Timothy B.
  20. Perturbation of Right Dorsolateral Prefrontal Cortex Makes Power Holders Less Resistant to Tempting Bribes By Yang Hu; Rémi Philippe; Valentin Guigon; Sasa Zhao; Edmund Derrington; Brice Corgnet; James J. Bonaiuto; Jean-Claude Dreher
  21. Dealing With Imperfect Randomization: Inference for the Highscope Perry Preschool Program By Heckman, James J.; Pinto, Rodrigo; Shaikh, Azeem M.

  1. By: Jules Gazeaud (CERDI - Centre d'Études et de Recherches sur le Développement International - IRD - Institut de Recherche pour le Développement - CNRS - Centre National de la Recherche Scientifique - UCA - Université Clermont Auvergne); Nausheen Khan (World Bank Group); Eric Mvukiyehe (Duke University); Olivier Sterck (UA - University of Antwerp, University of Oxford)
    Abstract: Is it possible to stimulate women's income-generating activities by relaxing their financial and human capital constraints? Does involving husbands help or hinder the effort? We examine these questions using a three-arm randomized-controlled trial with 2000 women in Tunisia. Women in the two treatment arms were offered a large cash grant (worth USD768 in PPP terms) and a gender-sensitive financial training. In one of the treatment arms, women were additionally encouraged to bring their male partner to the training. Two years after the program, we show that the treatments stimulated women's income-generating activities, but only when partners were not involved, and with no downstream effects on women's agency. Independently of partners' participation, impacts on household living standards were overwhelmingly positive, suggesting that the program was highly costeffective. Overall, our results highlight the difficulty of stimulating women's agency in traditional societies, and suggest that involving men in women's empowerment programs can backfire.
    Keywords: Cash Transfers, Financial Training, Gender Roles, Employment
    Date: 2023–10
    URL: http://d.repec.org/n?u=RePEc:hal:journl:hal-04364356&r=exp
  2. By: Andrej Woerner (LMU Munich); Giorgia Romagnoli (University of Amsterdam – CREED); Birgit M. Probst (TU Munich); Nina Bartmann (Duke University); Jonathan N. Cloughesy (Duke University & University of Southern California); Jan Willem Lindemans (Duke University)
    Abstract: Traditionally, incentives to promote behavioral change are assigned rather than chosen. In this paper, we theoretically and empirically investigate the alternative approach of letting people choose their own incentives from a menu of increasingly challenging and rewarding options. When individuals are heterogeneous and have private information about their costs and benefits, we theoretically show that leaving them the choice of incentives can improve both adherence and welfare. We test the theoretical predictions in a field experiment based on daily meditation sessions. We randomly assign some participants to one of two incentive schemes and allow others to choose between the two schemes. As predicted, participants sort into schemes in (partial) agreement with the objectives of the policy maker. However, in contrast to our prediction, participants who could choose complete significantly fewer sessions than participants that were randomly assigned. Since the results are not driven by poor selection, we infer that letting people choose between incentive schemes may bring in psychological effects that discourage adherence.
    Keywords: monetary incentives; dynamic incentives; field experiment; mental health;
    JEL: D03
    Date: 2023–12–08
    URL: http://d.repec.org/n?u=RePEc:rco:dpaper:475&r=exp
  3. By: Sophie Cêtre (IRSN/PSE-SANTE/SESUC/LERN - Laboratoire d'Economie du Risque Nucléaire - IRSN - Institut de Radioprotection et de Sûreté Nucléaire); Max Lobeck (University of Konstanz)
    Abstract: Do principals' distributive preferences affect the allocation of incentives within firms? We run a Principal-Agent lab experiment, framed as a firm setting. In the experiment, subjects are randomized in the principal or worker position. Principals must choose piece rate wage contracts for two workers that differ in terms of ability. Workers have to choose an effort level that is non-contractible. Principals are either paid in proportion to the output produced (Stakeholder treatment) or paid a fixed wage (Spectator treatment). We study how principals make trade-offs between incentive concerns (motivating workers to maximize output) and their own normative distributive preferences. We find that, despite the firm-frame and the moral hazard situation, principals do hold egalitarian concerns, as principals are on average willing to trade off their firm's performance (and so their own income) for more wage equality among their workers. The willingness to reduce inequality among workers is sensitive to both extensive and intensive margin incentives, which shows that principals' choices are shaped by incentives that they face themselves.
    Keywords: Fairness, Distributive preferences, Principal-agent, Social preferences
    Date: 2023–07
    URL: http://d.repec.org/n?u=RePEc:hal:journl:hal-04347515&r=exp
  4. By: Daugaard, Dan; Kent, Danielle; Servátka, Maroš; Zhang, Le
    Abstract: The global warming crisis is unlikely to abate while the world continues to collectively fund the extraction and burning of fossil fuels. Carbon divestment is urgently needed to ward off the impending climate emergency. Yet responsible investments still only account for a modest share of global assets. We conduct an incentivized artefactual field experiment to test whether framing divestment as a social norm, communicating it by a person with perceived credibility and expertise (a messenger), and highlighting optimistic attributes bolster responsible investment. Our subjects are investment professionals who have significant influence over the allocation of funds. We provide evidence that optimistic framing increases responsible investment. Assuming a comparable effect size, the observed increase would represent a $3.6 trillion USD global shift in asset allocations.
    Keywords: experiment, ESG, responsible investment, optimism, framing
    JEL: C93 G11
    Date: 2023–11–20
    URL: http://d.repec.org/n?u=RePEc:pra:mprapa:119388&r=exp
  5. By: Gary Charness (University of California, Santa Barbara,); Ismael Rodriguez-Lara (Universidad de Málaga and Chapman University)
    Abstract: Using the mind game, we provide experimental evidence that people are more likely to lie when they disclose non-personal information (e.g., reporting a number they thought of) compared with personal information (e.g., reporting the last digit of their birth year). Our findings suggest that the type of information is an important factor for lying behavior.
    Keywords: Lying behavior, personal information, impersonal information, selfconcept-maintenance, moral costs, motivated beliefs
    Date: 2024
    URL: http://d.repec.org/n?u=RePEc:chu:wpaper:24-01&r=exp
  6. By: Andrej Woerner (LMU Munich)
    Abstract: This paper introduces the matched-bet mechanism. The matched bet is an easily applicable and strictly budget-balanced mechanism that aims to help people overcome time-inconsistent behavior. I show theoretically that offering a matched bet helps both sophisticated and naive procrastinators to reduce time-inconsistent behavior. A field experiment on exercising confirms the theoretical predictions: offering a matched bet has a significant positive effect on gym attendance. Self-reported procrastinators are significantly more likely to take up the matched bet. Overall, the matched bet proves a promising device to help people not to procrastinate.
    Keywords: monetary incentives; market design; field experiment; health behavior;
    JEL: C93 D47 D90 I12
    Date: 2023–12–10
    URL: http://d.repec.org/n?u=RePEc:rco:dpaper:476&r=exp
  7. By: Salle, Isabelle (University of Ottawa); Gorodnichenko, Yuriy (University of California, Berkeley); Coibion, Olivier (University of Texas at Austin)
    Abstract: We study how individuals' memories of inflation shape their expectations about future inflation using both surveys and laboratory experiments. Recalling having lived through prior disinflations has pronounced effects on how long-lived people expect the current inflation episode to last. Information treatments in which we show people prior disinflationary experiences similarly strongly reduce inflation expectations of individuals on average and are often recalled as inflation memories months later. We also show that when people try to forecast inflation in the lab, the inflation dynamics in the game can affect their beliefs much like the inflation experienced in real life. Methodologically, we compare and contrast surveys and lab experiments and discuss the pros and cons of each method, emphasizing the general consistency across the two methodologies.
    Keywords: inflation experience, experiments, surveys, randomized control trial
    JEL: E3 E4 E5
    Date: 2023–12
    URL: http://d.repec.org/n?u=RePEc:iza:izadps:dp16670&r=exp
  8. By: Silvia Castro (LMU Munich); Clarissa Mang (LMU Munich)
    Abstract: Social pressure and stigma can hinder the adoption of available technologies, especially in the context of sensitive health issues. We run a field experiment on the take-up of menstrual products in Bangladesh and test a discussion-based intervention in a work setting. We vary participation in group discussions designed to break the silence around menstruation, where colleagues share their personal experiences. We find positive effects on the willingness to pay for a known menstrual product (sanitary pads) and on the adoption of a new technology (anti-bacterial menstrual underwear). Our results show changes in restrictive social norms around purchasing the products and lower perceived stigma around menstruation in general.
    Keywords: social norms; social pressure; stigma; technology adoption; group discussions; menstrual health management; menstrual hygiene; adverse health behavior;
    JEL: D91 I12 I15 O12
    Date: 2023–12–07
    URL: http://d.repec.org/n?u=RePEc:rco:dpaper:474&r=exp
  9. By: Ďuriník, Michal; Morita, Hodaka; Servátka, Maroš; Zhang, Le
    Abstract: How does group identity influence promotion decisions and what impact does it have on the performance of organizations through promotions? We provide answers based on two experiments in which we identify the effect of group identity on the employers’ preferences regarding whom to promote, their expectations of the post-promotion effort of promoted and non-promoted workers, and the post-promotion effort itself. In both experiments, we find strong evidence of group identity biasing the employers’ preferences. The observed group identity bias in the promotion decision significantly reduces efficiency. Contributions to the literature on promotions in organizations and discrimination in promotions are discussed.
    Keywords: Group identity, in-group favoritism, post-promotion effort, post-promotion productivity, promotion decision
    JEL: C91 J7 M50
    Date: 2023–11–30
    URL: http://d.repec.org/n?u=RePEc:pra:mprapa:119389&r=exp
  10. By: Andrea Kiss (Carnegie Mellon University); Robert Garlick (Duke University); Kate Orkin (University of Oxford); Luke Hensel (Peking University)
    Abstract: Worker sorting into tasks and occupations has long been recognized as an important feature of labor markets. But this sorting may be inefficient if jobseekers have inaccurate beliefs about their skills and therefore apply to jobs that do not match their skills. To test this idea, we measure young South African jobseekers’ communication and numeracy skills and their beliefs about their skill levels. Many jobseekers believe they are better at the skill in which they score lower, relative to other jobseekers. These beliefs predict the skill requirements of jobs where they apply. In two field experiments, giving jobseekers their skill assessment results shifts their beliefs toward their assessment results. It also redirects their search toward jobs that value the skill in which they score relatively higher—using measures from administrative, incentivized task, and survey data—but does not increase total search effort. It also raises earnings and job quality, consistent with inefficient sorting due to limited information.
    Keywords: jobseekers, worker matching, skills, beliefs, search effort, field experiments, South Africa
    JEL: C93 D83 J24 J31 O15
    Date: 2023–09
    URL: http://d.repec.org/n?u=RePEc:upj:weupjo:23-388&r=exp
  11. By: Brodeur, Abel; Cook, Nikolai M.; Hartley, Jonathan S.; Heyes, Anthony
    Abstract: Pre-registration is regarded as an important contributor to research credibility. We investigate this by analyzing the pattern of test statistics from the universe of randomized controlled trials (RCT) studies published in 15 leading economics journals. We draw two conclusions: (a) Pre-registration frequently does not involve a pre-analysis plan (PAP), or sufficient detail to constrain meaningfully the actions and decisions of researchers after data is collected. Consistent with this, we find no evidence that pre-registration in itself reduces p-hacking and publication bias. (b) When pre-registration is accompanied by a PAP we find evidence consistent with both reduced phacking and publication bias.
    Keywords: Pre-analysis plan, Pre-registration, p-Hacking, Publication, bias, Research credibility
    JEL: B41 C13 C40 C93
    Date: 2023
    URL: http://d.repec.org/n?u=RePEc:zbw:glodps:1147pre&r=exp
  12. By: Steven Tucker (University of Waikato); Yilong Xu (Utrecht University)
    Abstract: In an important contribution, Lei et al. (2001, Econometrica) argue that speculation is not the driver of bubbles in the absence of common knowledge of rationality, suggesting a focus on mistakes and confusion. We revisit Lei et al.’s (2001) design, confirming the existence of bubbles. However, we argue that, although their design removes the ability to speculate, it introduces several unintended design artifacts, inducing bubbles.
    Keywords: speculation; bubbles; cognitive ability; asset market experiment
    JEL: C91 G13
    Date: 2024–01–03
    URL: http://d.repec.org/n?u=RePEc:wai:econwp:24/01&r=exp
  13. By: Steven Tucker (University of Waikato); Yilong Xu (Utrecht University)
    Abstract: Research in Finance has long been intrigued by the causes of price bubbles. It has been argued that investors having doubts about the rationality of others may speculate on future capital gains. However, in an important contribution, Lei et al. (2001, Econometrica) argue that speculation is not the driver of bubbles in the absence of common knowledge of rationality, suggesting a focus on mistakes and confusion. Tucker and Xu (2024) revisit Lei et al.’s (2001) design, confirming the existence of bubbles, but argue that although their design removes the ability to speculate, it potentially introduces unintended design artifacts that may induce bubbles. We design a novel condition that eliminates incentives for speculation without these undesirable effects, which effectively eliminates bubbles even in the presence of confusion and/or lack of common expectations. We conclude that speculation plays a critical role in bubble formation, and thus does matter.
    Keywords: speculation; bubbles; cognitive ability; asset market experiment
    JEL: C91 G13
    Date: 2024–01–08
    URL: http://d.repec.org/n?u=RePEc:wai:econwp:24/02&r=exp
  14. By: Dalle, Axana (Ghent University); Lippens, Louis (Ghent University); Baert, Stijn (Ghent University)
    Abstract: As age discrimination hampers the OECD's ambition to extend the working population, an efficient anti-discrimination policy targeted at the right employers is critical. Therefore, the context in which age discrimination is most prevalent must be identified. In this study, we thoroughly review the current theoretical arguments and empirical findings regarding moderators of age discrimination in different demand-side domains (i.e. decision-maker, vacancy, occupation, organisation, and sector). Our review demonstrates that the current literature is highly fragmented and often lacks field-experimental evidence, raising concerns about its internal and external validity. To address this gap, we conducted a correspondence experiment and systematically linked the resulting data to external data sources. In so doing, we were able to study the priorly determined demand-side moderators within a single multi-level analysis and simultaneously control multiple correlations between potential moderators and discrimination estimates. Having done so, we found no empirical support for any of these moderators.
    Keywords: ageism, hiring discrimination, heterogeneity, literature review, field experiment, administrative data
    JEL: J71 J23 J14
    Date: 2023–12
    URL: http://d.repec.org/n?u=RePEc:iza:izadps:dp16672&r=exp
  15. By: Alec Brandon (Johns Hopkins University); Justin E. Holz (University of Michigan); Andrew Simon (The University of Chicago, Australian National University, Research School of Economics); Haruka Uchida (University of Chicago)
    Abstract: When minimum wages increase, employers may respond to the regulatory burdens by substituting away from disadvantaged workers. We test this hypothesis using a correspondence study with 35, 000 applications around ex-ante uncertain minimum wage increases in three U.S. states. Before the increases, applicants with distinctively Black names were 19 percent less likely to receive a callback than equivalent applicants with distinctively white names. Announcements of minimum wage hikes substantially reduce callbacks for all applicants but shrink the racial callback gap by 80 percent. Racial inequality decreases because firms disproportionately reduce callbacks to lower-quality white applicants who benefited from discrimination under lower minimum wages.
    Keywords: minimum wage, correspondence study, racial discrimination
    JEL: J23 C93 J71 J15
    Date: 2023–11
    URL: http://d.repec.org/n?u=RePEc:upj:weupjo:23-389&r=exp
  16. By: Davide Pace (LMU Munich); Taisuke Imai (Osaka University); Peter Schwardmann (Carnegie Mellon University); Joel van der Weele (Tinbergen Institute)
    Abstract: With a large representative survey (N=1, 128), we document that consumers are very uncertain about the emissions associated with various actions, which may affect their willingness to reduce their carbon footprint. We experimentally test two channels for the behavioural impact of such uncertainty, namely risk aversion about the impact of mitigating actions and the formation of motivated beliefs about this impact. In two large online experiments (N=2, 219), participants make incentivized trade-offs between personal gain and (uncertain) carbon impact. We find no evidence that uncertainty affects individual climate change mitigation efforts through risk aversion or motivated belief channels. The results suggest that reducing consumer uncertainty through information campaigns is not a policy panacea and that communicating scientific uncertainty around climate impact need not backfire.
    Date: 2023–12–02
    URL: http://d.repec.org/n?u=RePEc:rco:dpaper:470&r=exp
  17. By: Sania Ashraf; Cristina Bicchieri; Upasak Das. Alex Shpenev
    Abstract: Open defecation, which is linked with poor health outcomes, lower cognitive ability and productivity, has been widespread in India. This paper assesses the impact of a randomized norm-centric intervention implemented in peri-urban areas of Tamil Nadu in India on raising the value attached to residence in areas with a lower prevalence of open defecation, measured through Willingness to Pay (WTP). The intervention aimed to change social expectations about toilet usage through audio announcements, wall paintings, household visits, and community meetings. The findings indicate a significant increase in the WTP for relocating to areas with lower prevalence of open defecation. The results are consistent when using local average treatment effect estimations wherein the possibility of spillovers in the control areas is accounted for. They are also robust to potential bias due to local socio-political events during the study period and COVID-led attrition. We further observe a significant increase in toilet ownership and usage. While assessing the mechanism, we find that change in empirical expectations through the intervention (what one believes about the prevalence of toilet usage in the community) is one of the primary mediating channels. Normative expectations (what one believes about community approval of toilet usage) are found to have limited effect. The findings underscore the need for norm-centric interventions to propel change in beliefs and achieve long-term and sustainable sanitation behavior.
    Date: 2023–12
    URL: http://d.repec.org/n?u=RePEc:arx:papers:2312.16205&r=exp
  18. By: Marcel Preuss; Germán Reyes; Jason Somerville; Joy Wu
    Abstract: We examine how redistribution decisions respond to the source of luck when there is uncertainty about its role in determining opportunities and outcomes. We elicit redistribution decisions from a representative U.S. sample who observe worker outcomes and whether luck could determine earnings directly (Şlucky outcomesŤ) or indirectly by providing one of the workers with a relative advantage (Şlucky opportunitiesŤ). We Ąnd that participants redistribute less and are less responsive to changes in the importance of luck in environments with lucky opportunities. We show that individuals rely on a simple heuristic when assessing the impact of unequal opportunities, which leads them to underappreciate the extent to which small differences in opportunities can have a large impact on outcomes. These Ąndings have implications for models of redistribution attitudes and help explain the gap between lab evidence on support for redistribution and inequality trends.
    Keywords: Income inequality, demand for redistribution, fairness ideals
    JEL: C91 D63
    Date: 2024–01
    URL: http://d.repec.org/n?u=RePEc:bon:boncrc:crctr224_2024_491&r=exp
  19. By: Thomas, Ranjeeta; Galizzi, Matteo M.; Moorhouse, Louisa; Nyamukapa, Constance; Hallett, Timothy B.
    Abstract: Young people in sub-Saharan Africa are particularly at high risk of sexually transmitted infections. Little is known about their preferences and even less about their association with risky sexual behaviour. We conducted incentivized economic experiments to measure risk, time and prosocial preferences in Zimbabwe. Preferences measured at baseline predict biomarker and self-reported measures of risky sexual behaviour gathered 12 months later. We find robust evidence that individuals more altruistic at baseline are more likely to be Herpes Simplex Virus Type-2 (HSV-2) positive 12 months later. Analysis by sex shows this association is driven by our sample of women. Having more sexual partners is associated with greater risk tolerance amongst men and greater impatience amongst women. Results highlight heterogeneity in the association between preferences and risky sexual behaviour.
    Keywords: risk preference; time preference; altruism; social proximity; risky sexual behaviour; OPP1161471; Centre for Global Infectious Disease Analysis funding from the UK Medical Research Council and Department for International Development MR/R015600/1; R01MH114562-01; Elsevier deal
    JEL: I12 D91
    Date: 2024–01–01
    URL: http://d.repec.org/n?u=RePEc:ehl:lserod:121013&r=exp
  20. By: Yang Hu; Rémi Philippe; Valentin Guigon; Sasa Zhao; Edmund Derrington; Brice Corgnet (EM - emlyon business school); James J. Bonaiuto; Jean-Claude Dreher
    Abstract: Bribery is a common form of corruption that takes place when a briber suborns a power holder to achieve an advantageous outcome at the cost of moral transgression. Although bribery has been extensively investigated in the behavioral sciences, its underlying neurobiological basis remains poorly understood. Here, we employed transcranial direct-current stimulation (tDCS) in combination with a novel paradigm (N = 119 adults) to investigate whether disruption of right dorsolateral prefrontal cortex (rDLPFC) causally changed bribe-taking decisions of power holders. Perturbing rDLPFC via tDCS specifically made participants more willing to take bribes as the relative value of the offer increased. This tDCS-induced effect could not be explained by changes in other measures. Model-based analyses further revealed that such neural modulation alters the concern for generating profits for oneself via taking bribes and reshapes the concern for the distribution inequity between oneself and the briber, thereby influencing the subsequent decisions. These findings reveal a causal role of rDLPFC in modulating corrupt behavior.
    Keywords: corrupt behaviors, bribe taking, transcranial direct-current stimulation, dorsolateral prefrontal cortex, open data, open materials
    Date: 2022–03–01
    URL: http://d.repec.org/n?u=RePEc:hal:journl:hal-04325547&r=exp
  21. By: Heckman, James J. (University of Chicago); Pinto, Rodrigo (University of California, Los Angeles); Shaikh, Azeem M. (University of Chicago)
    Abstract: This paper considers the problem of making inferences about the effects of a program on multiple outcomes when the assignment of treatment status is imperfectly randomized. By imperfect randomization we mean that treatment status is reassigned after an initial randomization on the basis of characteristics that may be observed or unobserved by the analyst. We develop a partial identification approach to this problem that makes use of information limiting the extent to which randomization is imperfect to show that it is still possible to make nontrivial inferences about the effects of the program in such settings. We consider a family of null hypotheses in which each null hypothesis species that the program has no effect on one of many outcomes of interest. Under weak assumptions, we construct a procedure for testing this family of null hypotheses in a way that controls the familywise error rate – the probability of even one false rejection – in finite samples. We develop our methodology in the context of a reanalysis of the HighScope Perry Preschool program. We find statistically signicant effects of the program on a number of different outcomes of interest, including outcomes related to criminal activity for males and females, even after accounting for imperfections in the randomization and the multiplicity of null hypotheses.
    Keywords: exact inference, experiments, familywise error rate, imperfect randomization, multiple testing, multiple outcomes, permutation tests, Perry Preschool Program, program evaluation
    JEL: C31 I21 J13
    Date: 2023–12
    URL: http://d.repec.org/n?u=RePEc:iza:izadps:dp16675&r=exp

General information on the NEP project can be found at https://nep.repec.org. For comments please write to the director of NEP, Marco Novarese at <director@nep.repec.org>. Put “NEP” in the subject, otherwise your mail may be rejected.
NEP’s infrastructure is sponsored by the School of Economics and Finance of Massey University in New Zealand.