Introduction to Hypothesis Testing for Statistics 101
This article is meant to give an overview of the Hypothesis testing for Data science. It's not a deep dive into any particular topic. However, it's meant to give users a general (and hopefully an intuitive) understanding of hypothesis testing.
Hypothesis testing as the name suggests talks about testing the validity of our hypothesis. One might wonder what a hypothesis is?
A hypothesis is a simple experiment conducted to prove any assertion. Centuries ago, Copernicus set up to prove that the Earth was indeed round and not flat. He had a hypothesis (that the earth is round) and he gathered evidence for his assertion.
Null vs Alternative Hypothesis
Coming back to our previous example about Copernicus and his experiment to prove that the earth is round (Sorry not sorry flat earthers!)
During those times, the status quo or the commonly conceived notion was that the earth is flat. In statistical terms, this is called a Null hypothesis.
The null hypothesis, Hₒ is the commonly accepted fact; it is the opposite of the alternate hypothesis. Researchers work to reject, nullify or disprove the null hypothesis. Researchers come up with an alternate hypothesis, one that they think explains a phenomenon, and then work to…
