Arjada Bardhi (Northwestern University)

"Optimal Discovery and Influence through Selective Sampling"

26 gennaio 2018, 12:00


Most decisions – from a job seeker appraising a job offer to a policymaker assessinga novel social program – involve the consideration of numerous attributes of an objectof interest. This paper studies the optimal evaluation of a complex project of uncertainquality by sampling a limited number of its attributes. The project is described by a unitmass of correlated attributes, of which only one is observed initially. Optimal samplingand adoption is characterized under both single-agent and principal-agent evaluation. Inthe former, sampling is guided by the initial attribute but it is unaffected by its realization.Sequential and simultaneous sampling are equivalent. The optimal sample balances variabilityof sampled attributes with the importance of neighboring unsampled ones. Underprincipal-agent evaluation, the realization of the initial attribute informs sampling so asto better influence adoption. Sampling hinges on (i) its informativeness for the principal,and (ii) the variation of the agent’s posterior belief explained by the principal’s posteriorbelief. Optimal sampling is not necessarily a compromise between the players’ idealsamples. I identify conditions under which mild disagreement leads to excessively riskyor conservative sampling. Yet, drastic disagreement always induces compromise.