| This dissertation consists of three separate essays on the empirics of social interactions or social externalities. Chapter 1, 'Identifying social interactions through excess variance contrasts', outlines a new method for detecting and assessing the strength of social interactions based on contrasts in excess variance across social groups of exogenously differing sizes. An attractive feature of the approach is its robustness to the presence of group-level heterogeneity and sorting. The proposed estimation strategy is used to test for the presence of peer effects in learning using data from the Project STAR experiment. Generalized method-of-moments provides a unified framework for estimation and inference.; Chapter 2, 'Small sample properties of GMM and GEL estimation and inference procedures for social interactions models', studies the small sample properties of generalized method-of-moments (GMM) and generalized empirical likelihood (GEL) estimators and testing procedures. For linear IV-type models both two-step GMM and GEL achieve first order efficiency by replacing an infeasible optimal instrumental variable with a consistent estimate. GEL, unlike two-step GMM, uses a semiparametrically efficient estimate of this optimal instrument. As a result the first order conditions for GEL are asymptotically mean zero, while those for two-step GMM are not. Many discrepancies in the small sample performance of the two estimators and their associated inference procedures are attributable to this difference. The paper uses the social interactions model of Chapter 1 as an organizing example.; Chapter 3, 'Rich nations, poor nations: how much can multiple equilibria explain?' (coauthored with Jonathon Temple), examines social externalities at the macroeconomic level. The chapter asks whether the income gap between rich and poor nations can be explained by multiple equilibria. It explores the quantitative implications of a simple two sector general equilibrium model that gives rise to multiplicity, and calibrates the model for a large number of countries. Under the assumptions of the model, around a quarter of the world's economies are found to be in a low output equilibrium. The output gains associated with an equilibrium switch are sizeable. |
