Introduction
As discussed in the previous session, the linear regression model assumes a linear relationship between the response and predictor variables. But in some cases, the true relationship between the response and the predictors may be nonlinear. In this session, we will present a very simple method to directly extend the linear model to accommodate nonlinear relationships. But before that, we need to identify the nonlinearity present in the data.
In this session
We will try to answer the following questions:
- How to identify non-linearity in data especially in the presence of multiple variables in the model?
- What can we do when the relationship between the dependent and independent variable(s) is nonlinear?
Guidelines for in-module questions
The in-video and in-content questions given at the end of each segment are not graded. Note that graded questions are provided in a separate segment titled ‘Graded Questions’ at the end of this session. These questions will adhere to the guidelines given below.
| First Attempt Marks | Second Attempt Marks | |
| Questions With 2 Attempts | 10 | 5 |
| Questions With 1 Attempt | 10 | 0 |