Purchasing department cost drivers, multiple regression analysis (continuation of 10-37). (Chapter Appendix) Barry Lee decides that the simple regression analysis reported in Problem 10-37 could be extended to a multiple regression analysis. He finds the following results for several multiple regressions:

Regression 4. PDC = a + (bl X no. of POs) + (b2 Xno. of Ss)

Variable Coefficient Standard Error f-Value Constant $ 582,460 $ 308,872 1.89 Independent variable 1: no. ofPOs $ 147.86 $ 69.23 2.14 Independent variable 2: no. of Ss $3,542.80 $1,771.74 2.00 r2 = 0.63; Durbin-Watson statistic = 2.098. Adjusted R2 -= 0.529 Regression 5. PDC = « + (£, X no. of POs) + (b2 X no. of Ss) + (b^ X MP$)

Variable Coefficient Standard Error t-Value Constant $ 593,620 $ 372,246 1.59 Independent variable 1: no. of POs $ 148.86 $ 76.18 1.95 Independent variable 2: no. of Ss $3,580.87 $1,994.23 1.80 Independent variable 3: MP$ -0.0002 ' 0.0030 -0.07 r2 = 0.63; Durbin-Watson statistic = 2.09. Adjusted R2 = 0.45 The coefficients of correlation between pairwise combinations ofthe variables are PDC MP$ No. ofPOs MP$ 0.29 No. ofPOs 0.65 0.27 No. of Ss 0.63 0.34 0.29 Required L Evaluate regression 4 using the economic plausibility, goodness of fit, significance of independent variables, and specification analysis criteria. Compare regression 4 with regressions 2 and 3 in Problem 10-37. Which model would you recommend that Lee use? Why?

2. Compare regression 5 with regression 4. Which model would you recommend that Lee use? Why?

3. Lee estimates the following data for the Saskatoon store for next year: dollar value of mer¬

CHAPTER chandise purchased, $90,000,000; number of purchase orders, 3,900; number ofsuppliers, 110. How much should Lee budget for purchasing department costs for the Saskatoon store for next year?

4. What difficulties may arise in multiple regressions that do not arise in simple regressions?

Is there evidence ofsuch difficulties in either of the multiple regressions presented in this problem?

5. Give two examples of decisions where the regression results reported here (and in Problem 10-37) could be informative.