Empirical peer effects research often employs censored peer data. Individuals may list only a fixed number of links, implying mismeasured peer variables. I first document that censoring is widespread in network data. I then introduce an estimator and characterize its inconsistency analytically; an assumption on the ordering of peers implies that censoring causes attenuated peer effects estimates. Next, I demonstrate the effect of censoring in two data sets, showing that estimates with censored data underestimate peer influence. I discuss interpretation of estimates, propose methods for correction and bounding, and give implications for the design of network surveys.

Abstract Efforts to leverage peer effects by changing assignment have often fallen short due to endogenous peer choice. To address this, I build a two-part model: agents form networks via continuous linking decisions; conditional on realized networks, outcomes are determined. I provide results on identification of both parts of the model. Using data from a randomized study in India, I estimate the model, assess its performance in out-of-sample prediction, and simulate outcomes under preferential assignment rules. This paper contributes new methodology for identifying effects of alternative assignments in the presence of network endogeneity, as well as identification of network formation models.