Clustering Analysis of Micro Array Data

One such area of genetics research that has developed a great deal in the past several years has been micro arrays. Advancements in genetic research have often led to increased amounts of data but without efficient analyses techniques. The purpose of this project is to provide some examples of statistical methodology that can be used to analyze data from micro array experimentation. The data gathered from the micro array experimentation is contained in a 12,489 by 42 sized table. There are several different clustering techniques available to analyze the data. Kernel density estimation was used to compare the densities of different genes. Clustering methods used include hierarchical and least squares methods. With the hierarchical models, different distance parameters are determined and the results compared. The least squares method attempts to reduce the time it takes to cluster the data. The results from each method will be compared and different advantages and disadvantages will be discussed