Statistics

BUSINESS STATISTICS

ASSIGNMENT

SUBMITTED TO:
SIR ADNAN SIAL
SUBMITTED BY:
MEHREEN MEHBOOB
ROLL NO:
F19BB023
SECTION:
MORNING-B
Business statistics

Table 1:

Model Summary b
Model R R Square Adjusted R Std. Error of the Change Statistics Durbin-Watson
Square Estimate R Square Change F Change df1 df2 Sig. F Change
1 .518 a
.268 .263 .47841 .268 49.537 2 270 .000 2.001
a. Predictors: (Constant), TRANL, ICT
b. Dependent Variable: KIM
Interpretation:
In this model, TRANL AND ICT are predictors while KIM is dependent variable. This model is significant at p<0.5. The value of Adjusted R2 (.263)
which means 26.3% change in KIM is caused by TRANL and ICT. The value of Durbin-Watson is less than 3 which means there is no
autocorrelation.

Table 2:

Coefficients a
Model Unstandardized Coefficients Standardized t Sig. Correlations Collinearity Statistics
Coefficients
B Std. Error Beta Zero-order Partial Part Tolerance VIF
(Constant) 1.093 .235 4.648 .000
1 ICT .396 .051 .421 7.754 .000 .479 .427 .404 .919 1.088
TRANL .208 .055 .205 3.776 .000 .325 .224 .197 .919 1.088
a. Dependent Variable: KIM
Interpretation:
In this table, both ICT and TRANL are significant at p <0.01 Multi-collinearity does not exist because value of Tolerance >0.02 and VIF < 3. The
regression equation is ŷ =1.093+ 0.396X1 +.208X2 where ŷ is estimated value of KIM, X1 is ICT and X2 is TRANL. By putting values of X1 and X2
we can calculate ŷ.

Step wise regression

Model Summary c
Model R R Square Adjusted R Std. Error of the Change Statistics Durbin-Watson
Square Estimate R Square Change F Change df1 df2 Sig. F Change
1 .479 a
.230 .227 .48997 .230 80.862 1 271 .000
2 .518b
.268 .263 .47841 .039 14.257 1 270 .000 2.001

1
Business statistics

a. Predictors: (Constant), ICT

Interpretation:
In model 1, independent variable ICT is predictor and KIM is dependent variable and this model is significant at p<0.5 and value of adjusted R2
is .227 which means 22.7% change in KIM is caused by ICT.

Table 4:

Coefficients a
Model Unstandardized Coefficients Standardized t Sig. Correlations Collinearity Statistics
Coefficients
B Std. Error Beta Zero-order Partial Part Tolerance VIF
(Constant) 1.703 .175 9.722 .000
1
ICT .451 .050 .479 8.992 .000 .479 .479 .479 1.000 1.000
(Constant) 1.093 .235 4.648 .000
2 ICT .396 .051 .421 7.754 .000 .479 .427 .404 .919 1.088
TRANL .208 .055 .205 3.776 .000 .325 .224 .197 .919 1.088
a. Dependent Variable: KIM
In model 2, independent variable ICT and TRANL are predictors while KIM is dependent variable. This model is significant at p<0.5. The value of
Durbin-Watson is less than 3 which means there is no auto correlation. Model 2 is parsimonious. The value of R >0.5 and there is strong and positive
relationship between them. The value of Adjusted R2 which means 26.3% change in KIM is caused by TRANL and ICT.
Interpretation:
In model 1, regression equation is ŷ =1.703+ 0.451X where ŷ is estimated value of KIM, X is ICT. By putting values of X, we can calculate ŷ,
In model 2, both ICT and TRANL are significant at p <0.01 Multi-collinearity does not exist because value of Tolerance >0.02 and VIF < 3. The
regression equation is ŷ =1.093+ 0.396X1 +.208X2 where ŷ is estimated value of KIM, X1 is ICT and X2 is TRANL. By putting values of X1 and X2 we
can calculate ŷ.