TY  - JOUR
TI  - Problems and Testing the Assumptions of Linear Regression: a Machine Learning Perspective
AU  - Ayoosh Kathuria
AU  -  Baij Nath Kaushik
JO  - International Journal of Scientific Research in Computer Science, Engineering and Information Technology
PB  - Technoscience Academy
DA  - 2017/09/30
PY  - 2017
DO  - https://doi.org/10.32628/IJSRCSEIT
UR  - https://ijsrcseit.com/CSEIT174403
VL  - 2
IS  - 7
SP  - 16	
EP  - 25
AB  - Linear Regression is perhaps one of most well-known algorithms in statistics and Machine Learning. Despite its widespread use in machine learning applications, the importance of testing the assumptions of linear regression is often trivialised in machine learning literature. However, the predictions of linear regressions cannot be trusted unless its assumptions are met. An attempt has been made to attract the attention of the community towards this understated aspect of putting linear regression into practice. This paper serves as an endeavour to shed some light on ways to test the assumptions of linear regressions and how to remedy the violations if there are any.