When performing this task, a large Durbin-Watson statistic indicates an underestimation of statistical significance. If a set of values generated by this task have covariance zero, (-5[1])are mean zero, and are homoscedastic, (-5[1])then a method (10[1])for performing this task is (10[1])optimal by the Gauss-Markov theorem. (10[2]-5[1])Binary classification problems are solved using the “logistic” (10[4])form (10[1])of this (10[1]-5[1])task. (10[14])A form (10[1])of this (-5[1])task (10[1])seeks (10[1])to minimize (10[1])the sum of squared (10[3])residuals. (10[5]-5[3])The quantity (-5[1])r-squared (10[2])signifies (10[3])the (10[1])effectiveness of a form of this (10[1])task (10[2]-5[1])applied (10[3])to (10[2])data with a single independent variable. (10[1])For 10 points, name this task in statistics whose “linear” (10[1])type (10[1])involves (10[2])finding a (10[1])line (10[1])of best fit. (10[2])■END■ (10[5]0[2])