Using Hierarchical Clustering on Principal Component Analysis toCompare Civil Court Branches as Measured by Justice PerformanceIndicators

In both developing and developed countries, the performance of judicial units in justice system is measured by empirical indicators which are correlated with each other. The findings of existing indicator initiatives have traditionally been based on expert surveys, document reviews, and administrative data, or public surveys. This study combined principal component analysis (PCA) and cluster analysis in order to resolve the problem of evaluating multiple correlated indicators. Actually, hierarchical clustering on principal components (HCPC) is used to classify civil branches of a trial court in Iran to create a comprehensive evaluation. Based on PCA, the hierarchical clustering algorithm is applied, which divides justice performance indicators into three clusters based on the dissimilarity matrix. Then, three groups of that court branches were identified on the basis of the three variables. It allows justice system policymakers and reformers to measure individual courts’ performance and track backlog reduction and delay reduction programs. Further, this can help improve the operational level of justice indicators on justice systems, efficiency, accountability and credibility. The practical example illustrates the importance of the current approach to evaluating the performance of judicial units.