Cluster Analysis of Imputed Financial Data Using an Augmentation-Based Algorithm H. Bensmail and R. P. DeGennaro University of Tennessee, Knoxville,

CONTENTS 31.1 Introduction . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 513 31.2 Data and Preliminary Tests . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 514 31.3 Clustering and Bayesian Data Augmentation . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 518 31.4 Bayesian Model Selection for Choosing the Number of Clusters . . . . . 523 31.5 Analysis of Financial Data . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 523 31.6 Discussion . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 525

Acknowledgments . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 526 References . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 526

This paper introduces and applies a new statistical modelling technique to carry out cluster analysis on imputed financial companies data that offer a direct investment plan. We show how this new method correctly classifies the companies without Dividend Reinvestment Plans (DRIPS), and determines misclassified companies.