This repository has been created as part of my Data Science and Business Analytics Internship (GRIP) at the Sparks Foundation. The current task is to predict the percentage marks a student will score if he/she studies for a specified number of hours. The dataset contains 25 observations and it has been attached as the file student.txt.
The method used for analysis is Simple Linear Regression. In addition to the prediction step, the four important assumptions of regression have also been checked for the given data. These include:
- Linearity Assumption
- Constant Variance of Errors
- Non-correlated error terms
- Normality Assumption
Since there is only one predictor variable, the concept of multicollinearity does not apply and hence has not been discussed.