Sometimes, we don't have the ability to map every input to an output. For example, given a position X, what should the shooter RPM's be (Y)? Sometimes, we are able to record a couple of values and fit a function which can fill in every point in between.
It is important to note that we currently do not care much about the math or techniques of applied regresion, so don't try to understand it. Let's focus more on what we can do with the end result and how we can easily get there.
Watch the Regression Crash Course. You should be able to answer the following:
- Why Do We Care
- Where Can We Use It
One of the things to keep in mind when doing regression is interpolation and extrapolation.
Watch What is Interpolation and Extrapolation. You should be able to answer:
- What is interpolation
- What is extrapolation
- Which one is bad
There are a lot of ways that we can perform regression. Though some techniques more advanced than others, regression does not need to be complicated. In fact, it can be done automatically for us using Google Sheets.
You should be able to answer:
- How to record values
- How to plot values
- How to add a trend line
- How to display the equation of the trend line
We can use the R^2 value to determine best fit. The closer our value is to 1, the stronger our fit. Though this is not the end all, be all answer, it is typically a good guideline that shows how much of the variability your model is able to explain.