The Effects of Data Reduction Using Rough Set Theory on Logistic Regression Model

Logistic regression is a statistical technique for estimating the probability of a binary outcome, such as the existence or absence of a disease or a particular event. In this paper, a new integrated classification approach based on binary logistic regression analysis and rough set theory is presented. This new method is applied to two types of data sets, namely, anemia data and diabetes data. The results of the data analysis show that this method can improve the logistic regression model’s performance by removing inconsistent samples using the Rough Set Theory technique. There is a tendency that the increased model performance with this hybrid method is more visible on data that has many inconsistent samples.