Abstract: We report results of an experiment which uses within-subject design to elicit behaviour and stated beliefs in various versions of the p-beauty contest. We use two values of the multiplier parameter -- 1/2 and 2/3, -- and systematically vary the multiplier parameter  the number of contestants from two to nine individuals. We identify a subset of subjects with high strategic reasoning ability who are capable of `solving' the 2-player version of the contest but adjust their behaviour when facing multiple opponents. We also find evidence that a substantial proportion of subjects appears to misconceive the contest by failing to adjust for impact of own actions on the target number. Using an extended level-k model, we show that accounting for these types of behaviour significantly improves econometric fit. We also observe that subjects' behaviour changes when they interact with Large Language Models (LLMs) instead of humans. In particular, subjects act as if they expect greater tendency towards equilibrium behaviour from LLMs. Using qualitative data, we find evidence of alternative motivations for such behaviour.

Keywords: bounded rationality, strategic reasoning, beauty contest, models of others, game misconception, level-k.

Abstract: We present results of a series of laboratory experiments investigating stated beliefs and play in one-shot normal form games. We find that subjects’ stated beliefs about actions of their opponents are generally inconsistent with those implied by the standard (non-)equilibrium models of strategic thinking. We show that the shape of stated beliefs is systematically affected by the strategic structure of the game. Further, about 40% of subjects’ decisions in are inconsistent in the sense of expected payoff maximisation given stated beliefs. Using a series of treatments we investigate the role of decision-making errors, Knightian uncertainty, and risk. We show that errors in decision-making play a very limited role in explaining observed inconsistencies of decisions and stated beliefs. Rather, strategic uncertainty and risk are the key drivers behind the inconsistency. We propose a new model which reconciles decisions with stated and true beliefs.

Keywords: models of others, belief elicitation, Knightian uncertainty, risk, best response, decision-making errors.

Abstract: Contact tracing and quarantine programs have been one of the leading Non-Pharmaceutical Interventions against COVID-19. Some governments have relied on mandatory programs, whereas others embrace a voluntary approach. However, there is limited evidence on the relative effectiveness of these different approaches. In an interactive online experiment conducted on 731 subjects representative of the adult US population in terms of sex and region of residence, we find there is a clear ranking. A fully mandatory program is better than an optional one, and an optional system is better than no intervention at all. The ranking is driven by reductions in infections, while economic activity stays unchanged. We also find that political conservatives have higher infections and levels of economic activity, and they are less likely to participate in the contact tracing program.

Keywords: online experiment, contact tracing, quarantine, political ideology, welfare analysis.

Abstract: The outbreak of the COVID-19 pandemic led to an unprecedented rise in the use of social distancing as a means to curb the spread of infection. We examine the effectiveness of fines and informational messages (nudges) in promoting social distancing in a framed web-based interactive experiment conducted during the first wave of the pandemic on a near-representative sample of the US population. Fines promote distancing, while nudges have a smaller and less robust impact. Individuals do more social distancing when they are aware they are a superspreader. Using an instrumental variable approach, we show suggestive evidence that progressives are more likely to practice distancing, and they are somewhat more responsive to fines.
Keywords: social distancing, online experiment, nudge, superspreader, political ideology.

Abstract: On 11th Jan 2020, the first COVID-19 related death was confirmed in Wuhan, Hubei. The Chinese government responded to the outbreak with a lockdown that impacted most residents of Hubei province and lasted for almost three months. At the time, the lockdown was the strictest both within China and worldwide. Using an interactive web-based experiment conducted half a year after the lockdown with participants from 11 Chinese provinces, we investigate the behavioral effects of this ‘shock’ event experienced by the population of Hubei. We find that both one’s place of residence and the strictness of lockdown measures in their province are robust predictors of individual social distancing behavior. Further, we observe that informational messages are effective at increasing compliance with social distancing throughout China, whereas fines for noncompliance work better within Hubei province relative to the rest of the country. We also report that residents of Hubei increase their propensity to social distance when exposed to social environments characterized by the presence of a superspreader, while the effect is not present outside of the province. Our results appear to be specific to the context of COVID-19 and are not explained by general differences in risk attitudes and social preferences.

Keywords: social distancing, COVID-19, Wuhan lockdown, online experiment, nudge, superspreader.

Abstract: One of the most critical security protocol problems for humans is when you are betraying a trust, perhaps for some higher purpose, and the world can turn against you if you’re caught. In this short paper, we report on efforts to enable whistleblowers to leak sensitive documents to journalists more safely. Following a survey of cases where whistleblowers were discovered due to operational or technological issues, we propose a game-theoretic model capturing the power dynamics involved in whistleblowing. We find that the whistleblower is often at the mercy of motivations and abilities of others. We identify specific areas where technology may be used to mitigate the whistleblower’s risk. However we warn against technical solutionism: the main constraints are often institutional.