The factor technique is an extension of the unit method in which we sum the product of several quantities or components and add these to any components estimated directly. That is, (3'3) C=E Cd+E fmUmv d m Where C = cost being estimated; Cd = cost of the selected component dthat is estimated directly; fm = cost per unit of component m; Um = number of units of component m. As a simple example, suppose that we need a slightly refined estimate of the cost of a house consisting of 2,000 square feet, two porches, and a garage. Using a unit factor of $85 per square foot, $10,000 per porch, and $8,000 per garage for the two directly estimated components, we can calculate the total estimate as ($10, 000 x 2) + $8,000 + ($85 x 2,000) = $198, 000. * In addition, the observations should be independent. The difference between predicted and actual values is assumed to be normally distributed with an expected value of zero. Furthermore, the variance of the dependent variable is assumed to be equal for each value of the independent variable. All of the equation forms presented in Table 3-2 IEl can easily be transformed into a linear form. The following equations can be used to calculate the values of the coefficients b0 and b1 in the simple linear equation 3; = b0 + by: : (3'8) Ml a) (2%) 1:1 1:1 i=1 \"2963 2.\") , Z=1 i=1 (3'9) b0: Note that the variable n in the foregoing equations is equal to the number of data sets used to estimate the values of be and b1