IKH

Multiple Linear Regression

Introduction

Welcome to the session on ‘Multiple Linear Regression‘. So far, we have discussed simple linear regression, where the model is built using one independent variable only. But what if you have multiple independent variables? How do you make a predictive model in such a case? Building a multiple linear regression on top of such data is one such solution.

In this session

You will use the example of sales prediction using the TV marketing budget that you saw in the previous session to build a multiple linear regression model. But now, instead of just one variable, you will have three variables to deal with. The marketing budget will be split into three marketing channels: TV marketingradio marketing and newspaper marketing. You will see how adding more variables brings in many new problems and understand how to approach them. Finally, you will learn about feature selection and feature elimination to build the most optimal model.

This session is almost completely a theoretical session on multiple linear regression and its various aspects. So, don’t worry much if you don’t get everything in the first go; the concepts will become clearer when you see each of these aspects in action in the next session, which is a Python demonstration on multiple linear regression.

Guidelines for in-module questions

The in-video and in-content questions for this module are not graded. The graded questions are given in a separate segment at the end of the module. These questions will adhere to the following guidelines

First Attempt Marks
Second Attempt Marks
Questions
with 2 Attempts
105
Questions
with 1 Attempt
100

Report an error