Time now to get your hands dirty. Try increasing the random variation in the test data and see if that has any impact. Remember, the r-squared is a measure of the fit, of how much do we capture the variance, so the amount of variance, well... why don't you see if it actually makes a difference or not.

That's linear regression, a pretty simple concept. All we're doing is fitting a straight line to set of observations, and then we can use that line to make predictions of new values. That's all there is to it. But why limit yourself to a line? There's other types of regression we can do that are more complex. We'll explore these next.