TABLE 3.1 for Question 2,

Purchasing Department cost drivers, simple regression analysis Fashion Flair operates a chain of 10 retail department stores. Each department store makes its own purchasing decisions. Barry Lee, assistant to the president of Fashion Flair, is interested in better understanding the drivers of Purchasing Department costs. For many years, Fashion Flair has allocated Purchasing Department costs to products on the basis of the dollar value of inventory purchased. A $100 item is allocated 10 times as many overhead costs associated with the Purchasing Department as a $10 item. Barry recently attended a seminar titled 'Cost drivers in the retail industry'. In a presentation at the seminar, Couture Fabrics, a leading competitor, reported number of purchase orders and number of suppliers to be the two most important cost drivers of Purchasing Department costs. The dollar value of inventory purchased in each purchase order was not found to be a significant cost driver. Barry interviewed several members of the Purchasing Department at the Fashion Flair store on the Gold Coast. They believed that Couture Fabrics's conclusions also applied to their Purchasing Department. Barry Lee collects the following data for the most recent year for Fashion Flair's 10 retail department stores: Number of suppliers (no. of Ss) 132 222 11 Department store Sydney Bondi Canberra Gold Coast Perth Hobart Brisbane Melbourne Adelaide Double Bay Purchasing Department costs (PDCs) $1 523 000 1 100 000 547 000 2 049 000 1 056 000 529 000 1 538 000 1 754 000 1 612 000 1 257 000 Dollar value of inventory purchased (IP) $68 315 000 33 456 000 121 160 000 119 566 000 33 505 000 29 854 000 102 875 000 38 674 000 139 312 000 130 944 000 Number of purchase orders (no. of POs) 4357 2 550 1 433 5 944 2 793 1 327 7586 3 617 1 707 4731 190 23 33 104 119 208 201 Barry decides to use simple regression analysis to examine whether one or more of three variables (the last three columns in the table) are cost drivers of Purchasing Department costs. Required 1. Run the below regression models to estimate a and b Regression 1: PDCs = a +(bx IP$) Regression 2: PDCS = a + b * No. of POs) Regression 3: PDCS = a + (6 * No. of Ss) 2. Compare and evaluate the three simple regression models estimated by Barry Lee. Graph each one. Also, use the format employed in Table 3.1 to evaluate the information. 3. Do the regression results support Couture Fabrics's presentation about the Purchasing Department's cost drivers? 4. How might Barry gain additional evidence on drivers of Purchasing Department costs at each of Fashion Flair's stores? Table 3.1 Comparison of alternative cost functions for indirect manufacturing labour costs estimated with simple regression for Elegant Rugs Criterion Cost function 1: machine-hours as independent variable Cost function 2: direct manufacturing labour-hours as independent variable uring Economic plausibility A positive relationship between indirect manufacturing labour costs (technical support labour) and machine-hours is economically plausible in Elegant Rugs's highly automated plant. A positive relationship between indirect manufacturing labour costs and direct manufacturing labour-hours is economically plausible, but less so than machine-hours in Elegant Rugs's highly automated plant on a week-to-week basis. Goodness of fit IU p2 = 0.52; standard error of regression = $170.50. Excellent goodness of fit. p = 0.17; standard error of regression = $224.60.Poor goodness of fit. Significance The t-value of 3.30 is significant at the 0.05 level. The t-value of 1.43 is not significant at the 0.05 level. independent variable(s) Specification analysis of estimation assumptions Plot of the data indicates that assumptions of linearity, constant variance, independence of residuals (Durbin- Watson statistic = 2.05) and normality of residuals hold, but inferences drawn from only 12 observations are not reliable. Plot of the data indicates that assumptions of linearity, constant variance, independence of residuals (Durbin- Watson statistic = 2.26) and normality of residuals hold, but inferences drawn from only 12 observations are not reliable Purchasing Department cost drivers, simple regression analysis Fashion Flair operates a chain of 10 retail department stores. Each department store makes its own purchasing decisions. Barry Lee, assistant to the president of Fashion Flair, is interested in better understanding the drivers of Purchasing Department costs. For many years, Fashion Flair has allocated Purchasing Department costs to products on the basis of the dollar value of inventory purchased. A $100 item is allocated 10 times as many overhead costs associated with the Purchasing Department as a $10 item. Barry recently attended a seminar titled 'Cost drivers in the retail industry'. In a presentation at the seminar, Couture Fabrics, a leading competitor, reported number of purchase orders and number of suppliers to be the two most important cost drivers of Purchasing Department costs. The dollar value of inventory purchased in each purchase order was not found to be a significant cost driver. Barry interviewed several members of the Purchasing Department at the Fashion Flair store on the Gold Coast. They believed that Couture Fabrics's conclusions also applied to their Purchasing Department. Barry Lee collects the following data for the most recent year for Fashion Flair's 10 retail department stores: Number of suppliers (no. of Ss) 132 222 11 Department store Sydney Bondi Canberra Gold Coast Perth Hobart Brisbane Melbourne Adelaide Double Bay Purchasing Department costs (PDCs) $1 523 000 1 100 000 547 000 2 049 000 1 056 000 529 000 1 538 000 1 754 000 1 612 000 1 257 000 Dollar value of inventory purchased (IP) $68 315 000 33 456 000 121 160 000 119 566 000 33 505 000 29 854 000 102 875 000 38 674 000 139 312 000 130 944 000 Number of purchase orders (no. of POs) 4357 2 550 1 433 5 944 2 793 1 327 7586 3 617 1 707 4731 190 23 33 104 119 208 201 Barry decides to use simple regression analysis to examine whether one or more of three variables (the last three columns in the table) are cost drivers of Purchasing Department costs. Required 1. Run the below regression models to estimate a and b Regression 1: PDCs = a +(bx IP$) Regression 2: PDCS = a + b * No. of POs) Regression 3: PDCS = a + (6 * No. of Ss) 2. Compare and evaluate the three simple regression models estimated by Barry Lee. Graph each one. Also, use the format employed in Table 3.1 to evaluate the information. 3. Do the regression results support Couture Fabrics's presentation about the Purchasing Department's cost drivers? 4. How might Barry gain additional evidence on drivers of Purchasing Department costs at each of Fashion Flair's stores? Table 3.1 Comparison of alternative cost functions for indirect manufacturing labour costs estimated with simple regression for Elegant Rugs Criterion Cost function 1: machine-hours as independent variable Cost function 2: direct manufacturing labour-hours as independent variable uring Economic plausibility A positive relationship between indirect manufacturing labour costs (technical support labour) and machine-hours is economically plausible in Elegant Rugs's highly automated plant. A positive relationship between indirect manufacturing labour costs and direct manufacturing labour-hours is economically plausible, but less so than machine-hours in Elegant Rugs's highly automated plant on a week-to-week basis. Goodness of fit IU p2 = 0.52; standard error of regression = $170.50. Excellent goodness of fit. p = 0.17; standard error of regression = $224.60.Poor goodness of fit. Significance The t-value of 3.30 is significant at the 0.05 level. The t-value of 1.43 is not significant at the 0.05 level. independent variable(s) Specification analysis of estimation assumptions Plot of the data indicates that assumptions of linearity, constant variance, independence of residuals (Durbin- Watson statistic = 2.05) and normality of residuals hold, but inferences drawn from only 12 observations are not reliable. Plot of the data indicates that assumptions of linearity, constant variance, independence of residuals (Durbin- Watson statistic = 2.26) and normality of residuals hold, but inferences drawn from only 12 observations are not reliable