EXPLORATORY STATISTICS USING R PROGRAMMING FOR DIABETES MELLITUS DATASET

Abstract

Exploratory data analysis is a must in conducting every research. By going through the process we could organize the dataset, understand the variables, identify relationships between variables, choose the right model, and help find patterns in a dataset. In this research we choose a healthcare dataset concerning diabetes mellitus. We explored the dataset and came up with few conclusions. We identified the relationship between variables in the dataset with diabetes mellitus. The correlation between variables and the disease were presented in visual graphs. We developed R codes to assist analysis as well as graphical representations. While conducting the exploratory statistics we discovered the flaws of the data collection and proposed few steps to advance the research in a developing a predictive model.