Parameter estimation for high dimensional classification model on colon cancer microarray dataset

Abstract

Abstract In classification problems, logistic regression is among powerful techniques for discrimination. It provides directive probabilities of sample classification and interpretable coefficients. When it comes to model high dimensional dataset, however, logistic regression with its Newton-Raphson method of parameter estimation is no longer applicable, especially on low sample size and extremely high dimension. By applying cross-entropy algorithm on regularized logistic regression, it was able to well performing parameter estimation and highly accurate classification result.