Normal distribution
As a lot of things fall into the normal distribution, so we can standardize them. Convert them into a unitless, standard normal distribution ⇒ then we can do a bunch of cool things, predicting, etc.
Given a very large data set of measurements of a donut’s diameter, how can we know if we randomly picked up a donut out of 1000 donuts, what would be the probability of that diameter of the donut falls into a specific range?
Converting x into z: (xs are the values that we have, and z are the x in the standardized data set)
- Draw the normal distribution curve of your data
- Calculate the z score
- Calculate the area under the curve
- Use the z table to determine the area under the curve (as it is standardized, it applies to a vast majority of data sets)