We use correlation in statistical terms to denote the association between two quantitative variables. Note that we have used the term quantitative variables. This should be meaningful to you. If not, we suggest you pause here and go through Chapter 1, Exploratory Data Analysis Fundamentals.

When it comes to quantitative variables and correlation, we also assume that the relationship is linear, that is, one variable increases or decreases by a fixed amount when there is an increase or decrease in another variable. To determine a similar relationship, there is the other method that's often used in these situations, regression, which includes determining the best straight line for the relationship. A simple equation, called the regression equation, can represent the relation:

Let's examine this formula:

• Y = The dependent variable (the variable that you are trying to predict). It is often referred to as the outcome variable.
• X = The independent variable (the variable that you are using to predict Y). It is often referred to as the predictor, or the covariate or feature.
• a = The intercept.
• b = The slope.
• u = The regression residual.

If y represents the dependent variable and x represents the independent variable, this relationship is described as the regression of y on x. The relationship between x and y is generally represented by an equation. The equation shows how much y changes with respect to x.

There are several reasons why people use regression analysis. The most obvious reasons are as follows:

• We can use regression analysis to predict future economic conditions, trends, or values.
• We can use regression analysis to determine the relationship between two or more variables. 
• We can use regression analysis to understand how one variable changes when another also change. 

In a later section, we will use the regression function for model development to predict the dependent variable while implementing a new explanatory variable in our function. Basically, we will build a prediction model. So, let's dive further into the regression.