Machine Learning and Big Data

3Correlation and Regression

Mohd. Abdul Haleem Rizwan

Department of Mathematics, Muffakham Jah College of Engineering and Technology, Hyderabad, India

Abstract

The focus of this chapter is to show the relationship between correlation and regression analysis. Correlation may be considered first than regression analysis and simple correlation coefficient concept which provides the idea of linear relationship between two variables. The existence of any linear relationship between two variables can be shown by drawing a scatter diagram. There are invalidations and genuine changes of sources of both variables in the correlation coefficient and the value always lies amidst minus one (−1) and plus one (+1) if there is a movement of dispersed points close to the straight line depending on whether the relation is negative or positive. The straight line relation between the two variables can be found by least squares (LS) method. The simple correlation coefficient measures the linear regression by multiple linear regression model, we have more than two independent variables. The goodness of fit in this case is measured by coefficient of determination which is the square of the multiple correlation coefficient.

Keywords: Regression analysis, correlation coefficient, simple and multilinear regression models

3.1 Introduction

Correlation can be seen in daily life to represent some method of relationship. Correlation is observed in the foggy climate and outbreaks of breathlessness. The relationship ...