 This is linear regression, but most real-world problems have many covariates. In such a case, we would want to use the extension of linear regression called multiple regression. This is another parametric regression method, and since it's parametric, it also has a general form y is equal to f of x plus epsilon. But this time, f of x takes the form of the sum of products of p covariates and coefficients, that is beta zero plus beta one x one plus beta two x two all the way up to beta p x p. So the estimated value of the response variable y is given by this equation.