# R-Squared

R-Squared is a statistical term saying how good one term is at predicting another.  If R-Squared is 1.0 then given the value of one term, you can perfectly predict the value of another term.  If R-Squared is 0.0, then knowing one term doesn’t not help you know the other term at all.  More generally, a higher value of R-Squared means that you can better predict one term from another.

R-Squared is most often used in linear regression.  Given a set of data points, linear regression gives a formula for the line most closely matching those points.  It also gives an R-Squared value to say how well the resulting line matches the original data points.

The alerts server uses linear regression to determine how well one stock tracks another.  Some stocks typically move in similar directions at similar times.  The server picks the highest R-Squared value to say which stocks are the best match.  The server also has a minimum value for R-Squared; if a pair of stocks has an R-Squared below this minimum value, then the server does not see this as a useful pair.  See our free stock screener for examples.