I was helping someone with her introduction to statistics class when the question come up. The literal meaning is easy to understand: you want to test whether your hypothesis is correct or not, but surprisingly not a lot know what is being done for that purpose.
I remember the first time I learned about hypothesis testing. It was some time in the second year of my undergraduate degree in a class of bio-statistics. What I extracted from then was only the algorithm to hypothesis testing:
- Chuck in numbers to a formula, get the value x,
- Check x in a certain distribution probability table,
- Translate it to its p-value, and
- Reject null hypothesis if p-value is below 0.05.
I know how to do it up to that point, but I have absolutely no idea what I am doing there. What is p-value, what are those tables, why 0.05? Only later did I find out that a lot of people who are not mathematically-learned also know about hypothesis testing up to this point.