Professional Documents
Culture Documents
on
Regression analysis
Presented By :
Surendra Kumar Jha
Roll - 22
Finding frequency in SPSS
10.0
15.0
California 19 9.5 5.0 10.0 9.5
6.0
Northwest 12 6.0 0.0 1.5
South Northeast Midwest Southwest Rocky California Northwest
Total 200 100.0 Mountain
Finding descriptive statistics
Descriptive Statistics
Statistic Statistic Statistic Statistic Statistic Std. Error Statistic Statistic Statistic Std. Error Statistic Std. Error
Payroll expenditures in thousands 200 187812 1053 188865 30500.89 2313.359 32715.837 1070326021.861 2.231 0.172 6.075 0.342
Number of outpatients 200 813369 0 813369 98224.75 8405.008 118864.762 14128831686.905 3.071 0.172 13.438 0.342
Number of admissions 200 37264 111 37375 6831.84 469.953 6646.138 44171146.350 1.611 0.172 3.096 0.342
ANOVAa
Model Sum of Squares df Mean Square F Sig.
1 Regression 917537470637.845 1 917537470637.845 2657.640 .000b
Residual 68358541871.549 198 345245160.967
Total 985896012509.395 199
a. Dependent Variable:
Total Expediture in
thousands
b. Predictors: (Constant),
Number of personnel
Coefficientsa
Unstandardized Standardized
Model Coefficients Coefficients t Sig.
B Std. Error Beta
1 (Constant) -4060.492 1906.237 -2.130 0.034
Number of personnel 82.647 1.603 0.965 51.552 0.000
a. Dependent Variable: Total
Expediture in thousands
Simple regression Analysis
Null hypothesis (H0): p = 0 (there is no significant correlation between the total expenditure and no of
personnel)
Alternative hypothesis (H1): p #0 (there is a significant correlation between the total expenditure and no of
personnel)
b0= -4060.492, this means total expenditure (y) is decreased by 4060.492 when x1= 0
b1= 82.647 this means total expenditure(y) is increased by 82.647 when the value of number of perssonal (x 1) is
increased by 1 unit
(se) = which indicate the average variation of total expenditure lies in the regression line 18580.774
Correlation coefficient / coefficient of determination
Correlation coefficient ( r )
R= 0.965 , this means there is positive correlation between total expenditure and no of personnel
if r2 = 0.93 than we can interpret it as total variation of expenditure 93% is explain by no of personnel and remaining 7% explain by others
Null hypothesis (H0): p = 0 (there is no significant correlation between the total expenditure and no of
personnel)
Alternative hypothesis (H1): p = (there is a significant correlation between the total expenditure and no of
personnel)
Leve of significance = 0.01
Correlation coefficient
Correlations
Number of
Number of beds personnel
Number of beds Pearson 1 .753**
Correlation
Sig. (2-tailed) 0.000
N 200 200
Number of personnel Pearson .753** 1
Correlation
Sig. (2-tailed) 0.000
N 200 200
**. Correlation is significant at the 0.01
level (2-tailed).
Correlation matrix: This matrices of correlation coefficient between
different pair of variable
Correlations
Total Payroll
Number of Number of Number of Number of Expediture expenditures Number of
beds admissions outpatients Births in thousands in thousands personnel
Hospital Pearson Correlation -0.011 -0.096 0.084 -0.104 -0.002 0.028 0.020
Sig. (2-tailed) 0.879 0.178 0.239 0.142 0.974 0.689 0.780
N 200 200 200 200 200 200 200
Number of beds Pearson Correlation 1 .625** .340** .429** .711** .737** .753**
Sig. (2-tailed) 0.000 0.000 0.000 0.000 0.000 0.000
N 200 200 200 200 200 200
Number of admissions Pearson Correlation 1 .602 **
.856 **
.902 **
.848 **
.879**
Sig. (2-tailed) 0.000 0.000 0.000 0.000 0.000
N 200 200 200 200 200
Number of outpatients Pearson Correlation 1 .567 **
.629 **
.626 **
.644**
Sig. (2-tailed) 0.000 0.000 0.000 0.000
N 200 200 200 200
Number of Births Pearson Correlation 1 .713 **
.660 **
.697**
Sig. (2-tailed) 0.000 0.000 0.000
N 200 200 200
Total Expediture in thousands Pearson Correlation 1 .983 **
.965**
Sig. (2-tailed) 0.000 0.000
N 200 200
Payroll expenditures in Pearson Correlation 1 .952**
thousands Sig. (2-tailed) 0.000
N 200