Bayesian estimates from experimental data can be influenced by highly diffuse or “uninformative” priors. This paper gives examples of how diffuse priors can affect estimates, and discusses how practitioners can use their expertise to critique and select a prior.1

We design a lab-in-the-field experiment involving naturally occurring groups operating in three South-African townships. We introduce an incentives-based mechanism named “participatory incentives” consisting of monetary incentives that are awarded conditional on the group reaching a threshold of minimum level of joint contribution to a common project or good. We show that participatory incentives significantly raise average contribution levels (from 29 to 62% of the endowment) and are even more effective in the presence of highly deprived people. We complement the reduced form estimations of the experimental data with a structural model that sheds light on the role of subjects’ beliefs and responsiveness to a social norm of high cooperation.

We introduce a dynamic game of outbidding where two groups use violence to compete in a tug-of-war fashion for evolving public support. We fit the model to the canonical outbidding rivalry between Hamas and Fatah using newly collected data on Palestinian public support for these groups. Competition has heterogeneous effects, and we demonstrate that intergroup competition can discourage violence. Competition from Hamas leads Fatah to use more terrorism than it would in a world where Hamas abstains from terrorism, but competition from Fatah can lead Hamas to attack less than it otherwise would. Likewise, making Hamas more capable or interested in competing increases overall violence, but making Fatah more capable or interested discourages violence on both sides. These discouragement effects of competition on violence emerge through an asymmetric contest, in which we find that Fatah uses terrorism more effectively to boost its support, although Hamas has lower attack costs. Expanding on these results, we demonstrate that outbidding theory is consistent with a positive, negative, or null relationship between measures of violence and incentives to compete.

Is the working capital channel big, and does it vary across industries? To answer this question, I estimate a dynamic stochastic macro-finance model using firm-level data. In aggregate, I find a partial channel —about three-fourths of firms’ labor bill are borrowed. However, the strength of this channel varies across industries, reaching as low as one-half for retail firms and as high as one for agriculture and construction. This provides evidence that monetary policy could have varying effects across industries through the working capital channel.

A theoretically consistent structural model facilitates definition and measurement of use and non-use benefits of ecosystem services. Unlike many previous approaches that utilize multiple stated choice situations, we apply this conceptual framework to a travel cost random utility model and a consequential single referendum contingent valuation research design for simultaneously estimating use and non-use willingness to pay for environmental quality improvement. We employ Monte Carlo generated data to evaluate properties of key parameters and examine the robustness of this method of measuring use and non-use values associated with quality change. The simulation study confirms that this new method, combined with simulated revealed and stated preference data can generally, but not always, be applied to successfully identify use and non-use values of various ecosystems while consistency is ensured.

Separation or “perfect prediction” is a common problem in discrete choice models that, in practice, leads to inflated point estimates and standard errors. Standard statistical packages do not provide clear advice on how to correct these problems. Furthermore, separation can go completely undiagnosed in fitting advanced models that optimize a user-supplied log-likelihood rather than relying on pre-programmed estimation procedures. In this paper, we both describe the problems that separation can cause and address the issue of detecting it in empirical models of strategic interaction. We then consider several solutions based on penalized maximum likelihood estimation. Using Monte Carlo experiments and a replication study, we demonstrate that when separation is detected in the data, the penalized methods we consider are superior to ordinary maximum likelihood estimators.

Signaling games are central to political science but often have multiple equilibria, leading to no definitive prediction. We demonstrate that these indeterminacies create substantial problems when fitting theory to data: they lead to ill-defined and discontinuous likelihoods even if the game generating the data has a unique equilibrium. In our experiments, currently used techniques frequently fail to uncover the parameters of the canonical crisis-signaling game, regardless of sample size and number of equilibria in the data generating process. We propose three estimators that remedy these problems, outperforming current best practices. We fit the signaling model to data on economic sanctions. Our solutions find a novel U-shaped relationship between audience costs and the propensity for leaders to threaten sanctions, which current best practices fail to uncover.