Beth Ferrell is the Chief Operating Officer at Union Hospital in Buffalo, New York. She is analyzing the hospital’s overhead costs but is not sure whether nursing hours or the number of patient days would be the best cost driver to use for predicting the hospital’s overhead. She has gathered the following information for the last six months of the most recent year:

Requirements
1. Are the hospital’s overhead costs fixed, variable, or mixed? Explain.
2. Graph the hospital’s overhead costs against nursing hours. Use Excel or graph by hand.
3. Graph the hospital’s overhead costs against the number of patient days. Use Excel or graph by hand.
4. Do the data appear to be sound or do you see any potential data problems? Explain.
5. Use the high- low method to determine the hospital’s cost equation using nursing hours as the cost driver. Predict total overhead costs if 25,000 nursing hours are predicted for the month.
6. Ferrell runs a regression analysis using nursing hours as the cost driver to predict total hospital overhead costs. The Excel output from the regression analysis is as follows:

If 25,000 nursing hours are predicted for the month, what is the total predicted hospital overhead?
7. Ferrell then ran the regression analysis using number of patient days as the cost driver. The Excel output from the regression is shown here:

If 3,790 patient days are predicted for the month, what is the total predicted hospital overhead?
8. Which regression analysis (using nursing hours or using number of patient days as the cost driver) produces the best cost equation? Explain youranswer.

Transcribed Image Text:

Hospital Overhead Nursing of Patient Cost per Number Overhead Overhead Cost per Month July$476,000 24,00 3,720 August September$424,000 20,000 4,220 Costs Hours Days Nursing Hour Patient Day $19.83 $ 127.96 $512,000 26,000 4,320 $19.69118.52 21.20 100.47 October$448,000 22,500 3,470 $19.91 $ 129.11 $555,000 30,000 5,690 $18.50 97.54 $431,000 22,000 3,210 19.59 134 27 November December SUMMARY OUTPUT Nursing hours as cost driver Regression Statistics 3 Multiple R 4 R Square 5 Adjusted R Square 6 Standard Error 7 Observations 8 ANOVA 0.984895 0.970018 0.962523 SaricnceF 10 Regression 11 Residual 12 Total 13 14 15 1 12,642,572 449 12,642,572 449 129.414926 0.000341 4 390760884 97,690,221 Standard Error Lower 958 Coeficiens tStat P-vdue 95% 1b Intercept 131004.69 30448454 17 X Variable 1 18 4.303 11376 0013 46,466.228 215,543.149 17.735 14.26 1.253 1SUMMARY OUTPUT-Using number of patient days as cost driver Regression Stotistics 3 Multiple R 4 RSquare 5 Adjusted R Square 6 Standard Error 0.669396 0.585745 32 82099359 Observations 8 ANOVA F SignificonceF 0.0465 89 MS 10 Regression 11 Residua 1 8,724462,852 8724 462 852 8.099072 4 4308 870482 5 13,033 333 334 217,620 12 Total 14 15 16 Intercept 7 Stondar d Lowa Uppr 95% Coefidents -28077596 69.320.327 Pvalue 4.050 0.015 88,311.882 473,240.047 -18TxVanable1/-47.15.--16.568に-一2.846 0047 LL51 93153