Question

please Answer c

(Cost of Shipment) Although a regional express delivery service bases the charge for shipping a package on the package weight and distance shipped, its profit per package depends on the package size (volume of space that it occupies) and the size and nature of the load on the delivery truck. The company recently conducted a study to investigate the relationship between the cost, y, of shipment (in dollars) and the variables that control the shipping charge- package weight, ri (in pounds), and distance shipped, r2 (in miles). Ten packages were randomly selected from among the large number received for shipment and a detailed analysis of the cost of shipment was made for each package, with the results shown in Table 1. Table 1: The Shipping Cost Data, together with some fitting results from a linear model. four types of residuals Cook's d package cost weight distance predicted leverage ID ri i2 2.6 5.90 47 2 3.9 3.20 145 3 8.000 4.400 202 4 9.200 6.600 160 4.6542 (2) (1) 0.1120 -0.8834 -0.4547 -0.4825-0.4544 0.010 8.509 0.1490.509-0.262-0.284 -0.264 0.005 9.828 0.203-0.628 -0.323 0.362 -0.338 0.011 6.634 0.613 -2.234 -1.150 -1.848 -2.392 1.804 0.956 0.3472.456 1.264 1.565 1.797 0.435 7 14.500 6.500 24012.706 0.321 1.794 0.924 1.120 1.145 0.197 3.035 0.272 -1.135 -0.584 -0.685 0.656 0.058 0.336 0.321 1.336 0.688 0.835 0.8140.110 9200 400 5 4.400 0.750 280 6 1.500 0.700 80 8 1.900 4.500 53 9 1.000 0.600 100 10 14.000 7.500 190 12.142 0.306 1.858 0.956 1.148 1.179 0.193 It can be found that n- 10, Ey 61, and v 603.08. (c) The following questions are related to outlier detection. Answer each with appropriate i. Which observation is most outlying in terms of its predictor values? Does it make it ii. Which observation is the hardest to predict? Does it seem to make it to your outlier justification. to your outlier list? list? iii. Which observation is the most influential one?

Answer 1

i) The observation that is most outlying in terms of its predictor values is the 1st observation. Further it has the highest leverage value and is greater than 3 times the mean leverage value.So it may be considered as an outlier

ii) The observation hardest to predict is the 6th observation as it has the highest residual values. However we cannot be sure whether to treat it as an outlier

iii) The most influential observation is the 5th observation since the cook's distance value is greater than one for this observation