Member-only story
Regression analysis as an integral part of statistical hypothesis testing
Four years ago I went onto the Kaggle website and endeavoured to learn about machine learning. It was only later that I tried my hand at studying statistics. One subject that I have found to be inherent in both machine learning and statistical hypothesis testing is regression analysis.
Regression analysis is, therefore, a core concept of both machine learning and statistical hypothesis testing, but it was a part of statistics before it was in machine learning. In fact, regression analysis was used in statistical hypothesis testing long before it was used in machine learning.
Regression analysis was devised in the 19th century by the British scientist, Sir Francis Galton. Galton developed regression analysis whilst studying the inheritance of physical traits. He formulated the concept of regression to the mean, which laid the foundation for regression analysis.
Statisticians Karl Pearson Udny Yule developed the methodology of regression analysis, making it a fundamental tool in statistical hypothesis testing. Regression analysis was used to test hypotheses about relationships between variables and make predictions based on those relationships.
In the mid-20th century regression analysis began to be applied to the field of machine learning. The…