An algorithm for determining the number of mixture components on the bayesian mixture model averaging for microarray data

The major challenges on the statistical analysis of microarray data are the limited availability of samples, large number of measured variables and the complexity of distribution of the data obtained (e.g., multimodal). These phenomena could be considered in Bayesian method, used Bayesian Mixture Model (BMM) methods and Bayesian Model Averaging (BMA) methods. Modeling of Bayesian Mixture Model Averaging (BMMA) for microarray data was developed based on these two studies. One of the most important stages in BMMA is determination of the number of mixture components in the data setting as the most appropriate BMMA models. This paper proposes an algorithm for determining the number of mixture components in BMMA for microarray data. The algorithm is developed based on the simulation data generated from a case study of Indonesian and it has been implemented on the outside Indonesian microarray data. The results have succed to demonstrate two step algorithms, called Preliminary Process and Smoothing Process Algorithms, to the Indonesian case microarray data with the accuracy rate of 99.3690% and 99.9094% for the outside Indonesian microarray data.