Collaborative Research: Econometric Methods for Models with Clustered Data and Covariate-Adaptive Randomization

The research objective of this proposal is to develop and provide new inference tools for economists to analyze data in three specific contexts: (i) models where the data is grouped into possibly few heterogeneous clusters, (ii) randomized controlled experiments (RCEs) where baseline information is used during treatment assignment of experimental units, and (iii) a class of non-standard partially identified models that can be written as a union of functional inequalities. The proposal also includes three main educational objectives that are well integrated with the research projects: (i) facilitate interactions between graduate students in applied microeconomic fields and faculty in econometric theory, (ii) make research in econometric theory more palatable and accessible to undergraduate students, (iii) get graduate students actively involved in the research projects described below and promote econometrics as a field. Some of the proposed activities to accomplishing these objectives are: (a) development of two new courses (grad and undergrad), (b) development of a weekly reading group for grad students, and (c) hiring both undergraduate and graduate RAs, among other activities.