Line of Best Fit

The line of best fit is the single straight line drawn through a scatter plot that comes closest, overall, to all the data points. Once you have it, you can read off a prediction: for any input x, the height of the line at that x is your predicted y.

It is the visual heart of simple linear regression. The line is summarized by just two numbers — where it crosses the vertical axis (the intercept) and how steeply it tilts (the slope) — and the whole question of regression is really just: which slope and intercept make the line fit best?