Double Robust Mass-Imputation with Matching Estimators

HDR Candidate: Ali Furkan Kalay

Milestone: PhD Mid-candidature review 

Title: Double Robust Mass-Imputation with Matching Estimators

Time and date: 9am, Friday 10 December 2021

Zoom link: https://uqz.zoom.us/j/87283148872

Abstract:

This paper is the first chapter of my PhD thesis entitled “Essays on Administrative Data Methodologies.” I propose using a method named Double Score Matching (DSM) to do mass-imputation and present an application to make inferences with a non-representative sample. DSM is a k-Nearest Neighbors algorithm that uses two balance scores instead of covariates to reduce the dimension of the distance metric and thus to achieve a faster convergence rate. DSM mass-imputation and population inference are consistent if one of two balance score models is correctly specified. Simulation results show that the DSM performs better than recently developed double robust estimators when the data generating process has nonlinear confounders. The nonlinearity of the data generating process is a major concern because it cannot be tested, leading to a violation of the assumptions required to achieve consistency. Even if the consistency of the DSM relies on the two modelling assumptions, it prevents bias from inflating under such cases because DSM is a semiparametric estimator. The confidence intervals are constructed using a wild bootstrapping approach. The proposed bootstrapping method generates valid confidence intervals as long as DSM is consistent.