Many real-life settings of individual choice involve social interactions, causing targeted policies to have spillover effects. This article develops novel empirical tools for analysing demand and welfare effects of policy interventions in binary choice settings with social interactions. Examples include subsidies for health-product adoption and vouchers for attending a high-achieving school. We show that even with fully parametric specifications and unique equilibrium, choice data, that are sufficient for counterfactual demand prediction under interactions, are insufficient for welfare calculations. This is because distinct underlying mechanisms producing the same interaction coefficient can imply different welfare effects and deadweight-loss from a policy intervention. Standard index restrictions imply distribution-free bounds on welfare. We propose ways to identify and consistently estimate the structural parameters and welfare bounds allowing for unobserved group effects that are potentially correlated with observables and are possibly unbounded. We illustrate our results using experimental data on mosquito-net adoption in rural Kenya.

People’s value of their own time is a key input in public policy evaluations—these evaluations should account for time taken away from work or leisure as a result of policy. Measuring this value for the self-employed is challenging, as, by definition, it is not priced by the market. Using rich choice data collected from farming households in western Kenya, we show that households exhibit non-transitive preferences. As a result, neither market wages nor standard valuation techniques correctly measure participants’ value of time. Using a structural model, we identify the behavioural wedges in participants’ choices and find that distortions appear when households exchange cash either for time or for goods. Our model estimates suggest that valuing the time of the self-employed at 60% of the market wage is a reasonable rule of thumb.