The estimated regression equation by least squares method minimizes the sum of the Group of answer choices Absolute deviations between actual and predicted y values Differences between actual and predicted y values. Squared differences between actual and predicted y values None of the choices Absolute deviations between actual and predicted x values.

Squared differences between actual and predicted y

Step-by-step explanation:

The least squares regression method used in predictive modeling for linear regression models produces a best fit line which will minimize the square of the mean difference between the actual and projected or predicted values of the dependent, y variable. Hence, the when the sum of the squared value of the difference between the actual and predicted values (residual) are taken, the fit which gives the minimum sum of squared value is the best fit line upon which the estimated regression equation is based.

step-by-step explanation:

step-by-step explanation:

x^2 -12x + 36 + y^2 = 36

x^2 + y^2 = 12x

r^2 = 12rcos(theta)

r = 12 cos(theta)