Comparing the matching properties of Coarsened Exact Matching, Propensity Score Matching, and Genetic Matching in a nationwide observational data and a Monte Carlo experiment
MetadataShow full item record
Sample matching is one statistical technique that can be applied to observational data to archive covariate balance and thus aid in estimating causal effects in studies lacking of randomization. This thesis (a) describes three types of sample matching methodologies-Propensity Score Matching (PSM), Coarsen Exact Matching (CEM), and Genetic Matching (GM), and (b) demonstrates and compares their application using empirical data from the Early Childhood Longitudinal Study-Kindergarten Class of 1998–99 (ECLS-K) and simulated data with seven scenarios differing by non-linear and/or non-additive associations between exposure and covariates. The study shows that CEM produces higher multivariate balance and consistently less biased effect estimate then the other two methods, although for data containing many categorical covariates curse of dimensionality is a noticeable concern in CEM. PSM and GM can result in more matched samples but carry higher extrapolation and model dependence in effect estimate.
Showing items related by title, author, creator and subject.
Choi, Hojoon (uga, 2008-08)Recently, there has been growing concerns about health and an interest in nutrition in the U.S. food industry, and some unhealthy foods are emphasizing their health qualities by adding artificial nutrients . In this context, ...
Austin, Benjamin Piya (uga, 2007-12)The current fMRI study investigated the neural substrates of saccadic inhibition in humans using a delayed-match-to-sample (DMS) / delayed-non-match-to-sample (DNMS) paradigm adapted from Hasegawa et al.’s (2004) study of ...
Xu, Bing (uga, 2010-08)The Bankruptcy Abuse Prevention and Consumer Protection Act (BAPCPA) which was passed in 2005 significantly reshaped the bankruptcy laws in the U.S. In this dissertation, using different datasets and estimation methods, I ...