The management of Wheeler Company has decided to develop cost formulas for its major overhead activities. Wheeler uses a highly automated manufacturing process, and power costs are a significant manufacturing cost. Cost analysts have decided that power costs are mixed. The costs must be broken into their fixed and variable elements so that the cost behavior of the power usage activity can be properly described. Machine hours have been selected as the activity driver for power costs. The following data for the past eight quarters have been collected:

Quarter	Machine Hours	Power Cost
1	20,000	$26,000
2	25,000	$38,000
3	30,000	$42,500
4	22,000	$37,000
5	21,000	$34,000
6	18,000	$29,000
7	24,000	$36,000
8	28,000	$40,000

2. Using the high and low points (i.e., the high-low method), compute a power cost formula. (Note: Round variable rate to three decimal places.)

Total power cost = $_______ + ( $________ x Number of machine hours )

3. Use the method of least squares to compute a power cost formula. Evaluate the coefficient of determination.

Variable rate (to two decimal places)	$________	per machine hour
Fixed cost (to the nearest dollar)	$_________
Coefficient of determination (R2) (to one decimal place).	___________	%

4. Conceptual Connection: Rerun the regression, and drop the point (20,000, $26,000) as an outlier. Compare the results from this regression to those for the regression in Requirement 3. Which is better?

This regression looks better in terms of R squared.

or

The regression in question 3 looks better in terms of R squared.