We have a given population with some distribution.

Now, our goal is to sample and represent that distribution in some way. We need to give information about the data without showing the entire data. We need numerical representations of the data so that we can accurately compare the data to other data. This is extremely difficult. Perhaps it’s because there are so many options. I suppose some methods will work better than others depending on the population and its distribution.

Distance is a scalar value, so it can’t be negative...We should’t worry about squaring any values.

I’m used to functions.