#5240 1 Pg within 12 hrs Final Project, Part III
ltdprinwival
5239Topic_FinalProject_PartII.docxRunning Head: FINAL PROJECT PART II: MULTIPLE REGRESSION ANALYSIS
FINAL PROJECT PART II: MULTIPLE REGRESSION ANALYSIS 5
Final Project Part II: Multiple Regression Analysis
Student’s Name:
Course Name and Number:
Instructor’s Name:
Institution:
Date Submitted:
Multiple Regression Analysis:
Regression Equation:
The regression equation from the excel output is:
-1267666.157 + 178512.21*Staffed Beds_05 – 1117.15*Medicare Days_05 – 352.889*Medicaid Days_05 + 1935.23*Total Surgeries_05 + 333072.73*RN FTE_05 + 3752420.245*Occupation – 15595326.25*Ownership +7469768.966*System Membership – 6828203.672*Rural/Urban -17012822.3*Teaching Affiliation – 479.524*Age 65 plus_05 – Crime Rate + 523.368*Uninsured 2005
Predictor Variables Hypothesis:
Null Hypothesis [H0] = Total Operating Expense_05 doesn’t depend on predictor variable
Alternative Hypothesis [Ha] = Total Operating Expense_05 depends on predictor variable
The null hypothesis will be rejected when the predictor variables for the p-value from the regression output table is less than 0.05, besides total operating expense_05 will depend on that predictor value. Therefore, from the regression output table, the Total Operating Expense_05 depends on Staff Beds-05; Medicare Days-05; Total Surgeries_05; and RN FTE-05.
Table 1: Descriptive Statistics
|
|
Total operating expense_05 |
Staffed beds_05 |
Medicare Days_05 |
Medicaid Days_05 |
Total Surgeries_05 |
RN FTE_05 |
Crime rate/100,000 population (2005) |
|
Mean |
127421693.25 |
216.59 |
25092.15 |
10467.28 |
8979.78 |
309.17 |
6779.72 |
|
Standard Deviation |
148432310.15 |
190.36 |
23417.92 |
13362.20 |
9415.53 |
371.65 |
5083.50 |
|
|
|
|
|
|
|
|
|
|
|
Occupation |
Ownership |
System Membership |
Rural/Urban |
Teaching Affiliation |
Age 65 Plus 2005 |
Uninsured 2005 |
|
Mean |
1.062 |
0.198 |
0.642 |
0.296 |
0.222 |
14199.506 |
17508.975 |
|
Standard Deviation |
0.330 |
0.401 |
0.482 |
0.459 |
0.418 |
18511.493 |
23327.551 |
R-Square and Statistical Significance of Variables:
|
|
Coefficients |
P-value |
|
Intercept |
-1267666.157 |
0.939151172 |
|
Staffed Beds_05 |
178512.2197 |
0.005422116 |
|
Medicare Days_05 |
-1117.157268 |
0.001623752 |
|
Medicaid Days_05 |
-352.8893251 |
0.312201779 |
|
Total Surgeries_05 |
1935.232639 |
0.044914666 |
|
RN FTE_05 |
333072.7317 |
9.47512E-14 |
|
Occupation |
3752420.245 |
0.751448068 |
|
Ownership |
-15595326.25 |
0.090097222 |
|
System Membership |
7469768.966 |
0.341213027 |
|
Rural/Urban |
-6828203.672 |
0.443922383 |
|
Teaching Affiliation |
-17012822.3 |
0.114762722 |
|
Age 65 Plus 2005 |
-479.5243856 |
0.688908865 |
|
Crime rate/100,000 population (2005) |
-125.9836697 |
0.873962781 |
|
Uninsured 2005 |
523.368357 |
0.584511145 |
The Model R-Square value = 0.968
Interpretation:
The results above indicate that the total operating expenses depend positively significantly on four aspects that include Staffed Beds_05; Medicare Days_05; Total Surgeries_05; and RN FTE_05. As a consequence, with the purpose of reducing the total operating expenses, these four aspects should be taken into consideration. Furthermore, from the regression equation, it is evident that the variables have a positive sign, except Medicare Days; implying that increase in these variables, will correspondingly lead to an increase in the total operating expenses. For instance, a unit increase in total surgeries, RN FTE, and staffed beds will lead to an increase in total operating expenses by 1935.23, 333072.7317, and 178512.2197 respectively.
Reference
