Thursday 4 February 2021, 5.00PM to 6:00 PM
Speaker(s): Runan Xu, (Rutgers)
I establish asymptotic properties of M-estimators under finite populations with clustered data, allowing for unbalanced and unbounded cluster sizes in the limit. I distinguish between two situations that justify computing clustered standard errors: i) cluster sampling induced by random sampling of groups of units, and ii) cluster assignment caused by the correlated assignment of “treatment” within groups. The finite population cluster-robust asymptotic variance is found to be no “larger” than its infinite population counterpart. I also show that one should only use clustered standard errors when there is cluster sampling and (or) cluster assignment for a general class of estimators.
Admission: Staff and PhD