Multiple hypothesis testing in experimental economics List, John A.; Shaikh, Azeem M.; Xu, Yang
Experimental economics : a journal of the Economic Science Association,
12/2019, Letnik:
22, Številka:
4
Journal Article
Recenzirano
Odprti dostop
The analysis of data from experiments in economics routinely involves testing multiple null hypotheses simultaneously. These different null hypotheses arise naturally in this setting for at least ...three different reasons: when there are multiple outcomes of interest and it is desired to determine on which of these outcomes a treatment has an effect; when the effect of a treatment may be heterogeneous in that it varies across subgroups defined by observed characteristics and it is desired to determine for which of these subgroups a treatment has an effect; and finally when there are multiple treatments of interest and it is desired to determine which treatments have an effect relative to either the control or relative to each of the other treatments. In this paper, we provide a bootstrap-based procedure for testing these null hypotheses simultaneously using experimental data in which simple random sampling is used to assign treatment status to units. Using the general results in Romano and Wolf (Ann Stat 38:598–633,
2010
), we show under weak assumptions that our procedure (1) asymptotically controls the familywise error rate—the probability of one or more false rejections—and (2) is asymptotically balanced in that the marginal probability of rejecting any true null hypothesis is approximately equal in large samples. Importantly, by incorporating information about dependence ignored in classical multiple testing procedures, such as the Bonferroni and Holm corrections, our procedure has much greater ability to detect truly false null hypotheses. In the presence of multiple treatments, we additionally show how to exploit logical restrictions across null hypotheses to further improve power. We illustrate our methodology by revisiting the study by Karlan and List (Am Econ Rev 97(5):1774–1793,
2007
) of why people give to charitable causes.
We use experiments, guided by theory, to examine how an exogenous decrease in the value of an agent's outside option (e.g., a proxy for a reduction in alternative contracting opportunities) affects ...relational contracting across two institutional environments. In the pure relational contracting environment, principals respond to a reduction in agents' outside option by restructuring contracts to offer fewer payment guarantees. This exposes agents to more counter‐party risk and their actual profits fell well short of promised profits. This is mitigated when contracting institutions permit formal contracts to coexist with relational contracts. Extensive margin and intensive margin efficiency are mostly unaffected.
We assess the predictive power of a model of other-regarding preferences—inequality aversion—using a within-subject design. We run four different experiments (ultimatum game, dictator game, ...sequential-move prisonersʼ dilemma and public-good game) with the same sample of subjects. We elicit two parameters of inequality aversion to test several hypotheses across games. We find that within-subject tests can differ markedly from aggregate-level analyses. Inequality-aversion has predictive power at the aggregate level but performs less well at the individual level. The model seems to capture various behavioral motives in different games but the correlation of these motives is low within subjects.
oTree is an open-source and online software for implementing interactive experiments in the laboratory, online, the field or combinations thereof. oTree does not require installation of software on ...subjects’ devices; it can run on any device that has a web browser, be that a desktop computer, a tablet or a smartphone. Deployment can be internet-based without a shared local network, or local-network-based even without internet access. For coding, Python is used, a popular, open-source programming language. www.oTree.org provides the source code, a library of standard game templates and demo games which can be played by anyone.
In light of the growing attention that social norm interventions have garnered as policy tools, we review the current body of evidence on their effectiveness with respect to pro-environmental ...behaviors. We identify the various conceptualizations of social norms currently in use and inventory the experimental economics and social psychology literature that has examined the impacts of social norm interventions on pro-environmental behavior. For each study included in this inventory, we note several contextual features, the data collection and analytical methods used, and any significant main effects attributed to the social norm intervention. We also review several theoretical models of behavior that incorporate social norms. Based on this empirical and theoretical review, we draw a number of policy implications and identify avenues for future research on the role of social norms with respect to pro-environmental behavior.
•We developed a laboratory experiment to quantify patterns of food waste.•Among the labels studied, “Use by” generates the greatest value of predicted waste.•Subjects indicate differential value of ...waste depending on product and date label.•Value of predicted food waste increases with package size regardless of date label.
The presence of food waste, and ways to reduce it, has generated significant debate among industry stakeholders, policy makers, and consumer groups around the world. Many have argued that the variety of date labels used by food manufacturers leads to confusion about food quality and food safety among consumers. Here, we develop a between-subject, laboratory experiment with different date labels (Best by, Fresh by, Sell by, and Use by) for products (ready-to-eat cereal, salad greens, and yogurt) of different sizes and dates to evaluate how date labels influence the value of premeditated food waste of subjects, or their willingness to waste (WTW). Subjects have different WTW over products, sizes, and dates; we expect that ambiguity avoidance may prompt differences in the WTW. The WTW is greatest in the “Use by” treatment, the date label which may be the least ambiguous and suggestive of food safety. The WTW is the lowest for the “Sell by” treatment, which may be the most ambiguous date label about safety or quality for the consumer. Results from the mixed-design, repeated measures ANOVA provide evidence that subjects have different WTW by date labels over products.
Incentivized methods for eliciting subjective probabilities in economic experiments present the subject with risky choices that encourage truthful reporting. We discuss the most prominent elicitation ...methods and their underlying assumptions, provide theoretical comparisons and give a new justification for the quadratic scoring rule. On the empirical side, we survey the performance of these elicitation methods in actual experiments, considering also practical issues of implementation such as order effects, hedging, and different ways of presenting probabilities and payment schemes to experimental subjects. We end with a discussion of the trade-offs involved in using incentives for belief elicitation and some guidelines for implementation.
Vaccination as personal public-good provision Reddinger, J. Lucas; Charness, Gary; Levine, David
Journal of economic behavior & organization,
August 2024, 2024-08-00, Letnik:
224
Journal Article
Recenzirano
Odprti dostop
Vaccination against infectious diseases has both private and public benefits. We study whether social preferences – concerns for the well-being of other people – are associated with one’s decision ...regarding vaccination. We measure these social preferences for 549 online subjects with a public-good game and an altruism game. To the extent that one gets vaccinated out of concern for the health of others, contribution in the public-good game is analogous to an individual’s decision to obtain vaccination, while our altruism game provides a different measure of altruism, equity, and efficiency concerns. We proxy vaccine demand with how quickly a representative individual voluntarily took the initial vaccination for COVID-19 (after the vaccine was widely available). We collect COVID-19 vaccination history separately from the games to avoid experimenter-demand effects. We find a strong result: Contribution in the public-good game is associated with greater demand to voluntarily receive a first dose, and thus also to vaccinate earlier. Compared to a subject who contributes nothing, one who contributes the maximum ($4) is 58% more likely to obtain a first dose voluntarily in the four-month period that we study (April through August 2021). In short, people who are more pro-social are more likely to take a voluntary COVID-19 vaccination. Behavior in our altruism game does not predict vaccination. We recommend further research on the use of pro-social preferences to help motivate individuals to vaccinate for other transmissible diseases, such as the flu and HPV.
•Individual contribution in a public-good game predicts vaccination in the field.•Results hint that a preference for equity is an underlying mechanism for vaccination.•We add to a body of evidence that economics lab measurements predict field behavior.•We offer insight into how behavioral health policy may yet harness social preferences.