Linear regression is one of those old-school statistical modeling approaches that are still popular. With the development of new languages and libraries, it is now in a much-improved version and much easier to work on. In my last article, I explained the development of a Simple Linear Regression method and analysis in detail. If you haven’t seen it, here is the link:

Multiple linear regression is an extension of simple linear regression. In simple linear regression, we worked on the relationship between one independent variable or explanatory variable and one dependent variable or response variable. Simple linear regression uses this very common general formula:

y = mx + c

where,

y = dependent variable or response variable

x = independent variable or explanatory variable

m = slope

c = intercept

If x and y share a linear relationship, you can predict ‘y’ if you have the ‘x’ data available.

In statistics, beta0 and beta1 are used instead of c and m. So, the formula becomes: