This team exercise uses the data in the file HospLab. (notice the 2 worksheet tabs in the excel file)
There are three independent variables. The objective is to determine the best individual variable or combination of variables to predict the number of hours of labor needed. With three independent variables there are seven possible models. There are some close calls, so be sure and use at least three decimal place accuracy.
For each model determine whether it is statistically significant at the .02 level of significance. For the models that survive the cut of statistical significance, determine which is the best model (again, it's a close call). For the best model predict the number of hours needed if X1 = 10,000, X2 = 2000, and X3 = 8.00. Use whatever values you need; you may or may not need all.
Be sure to back up your conclusions with appropriate values.
Submit your conclusions and the Excel or Minitab files to support your conclusions.
Please see the attachments. Calculations are done in MS Excel.
The data represents the need for labor in 16 U.S. Naval hospitals.
Variables in the data are
Y : Monthly labor hours required
X1: Monthly X ray exposure
X2: monthly occupied days (a hospital has one occupied bed day if one bed is occupied for an entire day
X3: average length of patients' stay in days
The regression model suggested is
Y = b0+b1X1+b2X2+b3X3
The parameters are estimated using the method of least squares.
Multiple R 0.99806
R Square 0.996125
Adjusted R ...
The solution gives the multiple regression analysis for hospital data in Minitab. The answer contain slope, intercept, correlation, r-square, coefficient of determination and regression coefficients. Interpretations of the results obtained are also included.