search for




 

Initialization method of finite mixture model using kernel density estimation and application on model-based clustering
Journal of the Korean Data & Information Science Society 2018;29:327-38
Published online March 31, 2018
© 2018 Korean Data and Information Science Society.

Hyun-ju Cho1 · Yeojin Chung2 · Youngmin Kim3

12e Consulting
2College of Business Administration, Kookmin University
3Department of Statistics, Kyungpook National University
Correspondence to: Assistant professor, College of Business Administration, Kookmin University, Seoul 02707, Korea. E-mail: ychung@kookmin.ac.kr
Received February 22, 2018; Revised March 16, 2018; Accepted March 19, 2018.
This is an Open Access article distributed under the terms of the Creative Commons Attribution Non-Commercial License (http://creativecommons.org/licenses/by-nc/3.0) which permits unrestricted non-commercial use, distribution, and reproduction in any medium, provided the original work is properly cited.
Abstract
The finite mixture model is widely used for model-based cluster analysis. The EM algorithm finds the maximum likelihood estimates of the finite mixture model. Since the performance of the EM algorithm is largely influenced by its initial value, the choice of the initial value has been regarded as an important factor for EM. This study proposes a new initialization method for the EM algorithm using the kernel density estimator. The location of modes of the kernel density estimate is calculated by the MEM algorithm and set as an initial value for component means for Gaussian mixture model. Simulation study and application on corporate default data show that the proposed method gives parameter estimates higher than the exising methods. In addition, we apply the model-based clustering based on the estimated mixture model and compare the performance of clustering.
Keywords : EM algorithm, finite mixture model, initial value, maximum Likelihood Estimation, model-based clustering.