Comparison of clustering algorithms on generalized propensity score in observational studies: a simulation study

• Published in: Journal of statistical computation and simulation Vol. 83; no. 12; pp. 2206 - 2218
• Main Authors: Tu, Chunhao, Jiao, Shuo, Koh, Woon Yuen
• Format: Journal Article
• Language: English
• Published: Abingdon Taylor & Francis 01.12.2013; Taylor & Francis Ltd
• Subjects: Algorithms; Cluster analysis; Clustering; Clusters; Comparative analysis; Computer simulation; Fuzzy; fuzzy c-means clustering algorithm; Fuzzy logic; Fuzzy set theory; generalized propensity score; k-means clustering algorithm; model-based clustering algorithm; observational studies; partitioning around medoids algorithm; Performance indices
• ISSN: 0094-9655; 1563-5163
• DOI: 10.1080/00949655.2012.685169

In observational studies, unbalanced observed covariates between treatment groups often cause biased inferences on the estimation of treatment effects. Recently, generalized propensity score (GPS) has been proposed to overcome this problem; however, a practical technique to apply the GPS is lacking. This study demonstrates how clustering algorithms can be used to group similar subjects based on transformed GPS. We compare four popular clustering algorithms: k-means clustering (KMC), model-based clustering, fuzzy c-means clustering and partitioning around medoids based on the following three criteria: average dissimilarity between subjects within clusters, average Dunn index and average silhouette width under four various covariate scenarios. Simulation studies show that the KMC algorithm has overall better performance compared with the other three clustering algorithms. Therefore, we recommend using the KMC algorithm to group similar subjects based on the transformed GPS.