Least squares method (LSM)

• It is a procedure hat minimizes the vertical deviations of plotted points surrounding a straight line.
• We are able to construct a best fitting straight line to the scatter diagram points and formulate a regression equation.

Unexplained variance

• 49% is due to fertilizer but what about 51%. It remains unexplained. Prediction hence is not perfect.
• For each value of x, we know the approx.. value of 4 but not the exact value.

Note:

i) The score that falls exactly on the regression line are called predicted scores.

ii) Line of best fit: It is a line that minimizes the distance of the actual score from the predicted score.