Master of Business Administration
University of Uva Wellassa
Assignment no 01
Business statistics
MBA 531-2
Index No :
UWU/PGU/MBA/03/02
Name: R.M.N.H.Rathnayake
Semester: 02
Submission Date: 10/09/2024
1|Page
01. Estimate the regression model using a statistical software and indicate the
output of the regression model
Regression Analysis: Design Point versus Vm, Vmc, Vb, Vd, Vc, Fb, Fd, Fc
Analysis of Variance
Source DF Adj SS Adj MS F-Value P-Value
Regression 8 630.26 78.782 1.02 0.450
Vm 1 8.09 8.089 0.11 0.749
Vmc 1 52.35 52.349 0.68 0.419
Vb 1 95.67 95.665 1.24 0.278
Vd 1 110.02 110.019 1.43 0.245
Vc 1 4.30 4.304 0.06 0.815
Fb 1 12.56 12.561 0.16 0.690
Fd 1 45.52 45.518 0.59 0.451
Fc 1 9.59 9.586 0.12 0.728
Error 21 1617.24 77.012
Total 29 2247.50
2|Page
Interpret the regression coefficients.
01. Regression equation
Regression Equation
Design Point = 17.3 - 0.132 Vm - 0.214 Vmc + 6.72 Vb - 6.83 Vd + 1.81 Vc + 1.44 Fb
- 2.55 Fd+ 2.09 Fc
.
02. Interpretation
Interpretation of the Coefficients:
Each coefficient in the regression equation represents the expected change in the Design
Point for a one-unit change in the corresponding variable, assuming all other variables are
held constant.
1. Constant (17.3):
o If all independent variables are zero, the predicted value of the Design Point
would be 17.3.
2. Vm (-0.132):
o For every one-unit increase in Vm, the Design Point is expected to decrease
by 0.132 units, holding all other variables constant. However, this effect is
not statistically significant (P-value = 0.749).
3. Vmc (-0.214):
o For every one-unit increase in Vmc, the Design Point decreases by 0.214
units, holding all other variables constant. This effect is also not statistically
significant (P-value = 0.419).
4. Vb (+6.72):
o For every one-unit increase in Vb, the Design Point increases by 6.72 units,
holding all other variables constant. This is the largest positive coefficient,
suggesting a strong potential influence on Design Point, but it is not
statistically significant (P-value = 0.278).
5. Vd (-6.83):
o For every one-unit increase in Vd, the Design Point decreases by 6.83 units,
holding all other variables constant. This is a large negative effect but is not
statistically significant (P-value = 0.245).
6. Vc (+1.81):
o For every one-unit increase in Vc, the Design Point increases by 1.81 units,
holding all other variables constant. This is also not statistically significant
(P-value = 0.815).
3|Page
7. Fb (+1.44):
o For every one-unit increase in Fb, the Design Point increases by 1.44 units,
but this effect is not statistically significant (P-value = 0.690).
8. Fd (-2.55):
o For every one-unit increase in Fd, the Design Point decreases by 2.55 units,
but this is not significant either (P-value = 0.451).
9. Fc (+2.09):
o For every one-unit increase in Fc, the Design Point increases by 2.09 units,
though this effect is also not significant (P-value = 0.728).
Overall Interpretation:
None of the coefficients are statistically significant (all P-values are greater than
0.05). This means that there is no strong evidence that any of the independent
variables (Vm, Vmc, Vb, Vd, Vc, Fb, Fd, Fc) have a meaningful impact on the
Design Point.
Although some variables like Vb and Vd have large coefficients, the lack of
statistical significance means we cannot confidently conclude that these variables
truly affect the Design Point.
03. Determine the statistical significance of estimated coefficients.
Coefficients
Term Coef SE Coef T-Value P-Value VIF
Constant 17.3 18.6 0.93 0.362
Vm -0.132 0.406 -0.32 0.749 2.55
Vmc -0.214 0.260 -0.82 0.419 2.18
Vb 6.72 6.03 1.11 0.278 13.95
Vd -6.83 5.72 -1.20 0.245 22.78
Vc 1.81 7.64 0.24 0.815 19.36
Fb 1.44 3.58 0.40 0.690 23.85
Fd -2.55 3.32 -0.77 0.451 6.34
Fc 2.09 5.92 0.35 0.728 37.61
To determine the statistical significance of the estimated coefficients, we look at the **P-
Values** corresponding to each coefficient in the regression model. The general rule is:
- If the **P-Value** is less than **0.05**, the coefficient is considered **statistically
significant** at the 5% significance level. This means the variable has a significant
4|Page
relationship with the dependent variable (Design Point).
- If the **P-Value** is greater than **0.05**, the coefficient is **not statistically
significant**, meaning there isn't enough evidence to conclude that the variable has an
effect on the dependent variable.
Coefficients and their P-Values from the model:
| Term | Coefficient | P-Value | Significance |
|----------- |------------- |--------- |--------------|
| Constant | 17.3 | 0.362 | Not Significant |
| Vm | -0.132 | 0.749 | Not Significant |
| Vmc | -0.214 | 0.419 | Not Significant |
| Vb | 6.72 | 0.278 | Not Significant |
| Vd | -6.83 | 0.245 | Not Significant |
| Vc | 1.81 | 0.815 | Not Significant |
| Fb | 1.44 | 0.690 | Not Significant |
| Fd | -2.55 | 0.451 | Not Significant |
| Fc | 2.09 | 0.728 | Not Significant |
Interpretation:
None of the coefficients are statistically significant** because all the P-Values are greater
than 0.05.
This means that based on this dataset, there is **no strong evidence** to suggest that any
of the independent variables (Vm, Vmc, Vb, Vd, Vc, Fb, Fd, Fc) significantly affect the
dependent variable (Design Point).
In conclusion, the estimated coefficients are not statistically significant at the 5%
significance level. Therefore, we cannot confidently say that any of these variables have a
meaningful influence on the Design Point.
5|Page
04. Overall significance of the model.
The overall significance of the model is determined by the F-Value and the corresponding
P-Value from the Analysis of Variance (ANOVA) table.
In this case:
F-Value = 1.02
P-Value = 0.450
A model is considered statistically significant if the P-Value is less than the commonly
used significance level (usually 0.05). Since the P-Value is 0.450, which is much higher
than 0.05, the model is not statistically significant overall.
This indicates that the independent variables (Vm, Vmc, Vb, Vd, Vc, Fb, Fd, Fc) do not
jointly explain a significant portion of the variation in the dependent variable (Design
Point). The model does not provide enough evidence to conclude that there is a meaningful
relationship between the predictors and the response variable.
6|Page
Create scatter plots with all independent variables against the dependent
variable.
Scatterplot of Design Point vs Fd
30
25
20
Design Point
15
10
0
1 2 3 4 5 6 7
Fd
7|Page
Scatterplot of Design Point vs Fc
30
25
20
Design Point
15
10
0
3 4 5 6 7 8 9 10
Fc
Scatterplot of Design Point vs Fb
30
25
20
Design Point
15
10
0
1 2 3 4 5 6 7 8 9 10
Fb
8|Page
Scatterplot of Design Point vs Vc
30
25
20
Design Point
15
10
0
1 2 3 4 5 6
Vc
Scatterplot of Design Point vs Vd
30
25
20
Design Point
15
10
0
2 3 4 5 6 7 8
Vd
V
9|Page
Scatterplot of Design Point vs Vb
30
25
20
Design Point
15
10
0
2 3 4 5 6
Vb
Scatterplot of Design Point vs Vmc
30
25
20
DesignPoint
15
10
0
0 10 20 30 40 50 60
Vmc
10 | P a g e
Scatterplot of Design Point vs Vm
30
25
20
Design Point
15
10
0
30 35 40 45 50 55
Vm
Correlation: Design Point, Vm, Vmc, Vb, Vd, Vc, Fb, Fd, Fc
Design Point Vm Vmc Vb Vd
Vm -0.337
0.068
Vmc -0.376 0.701
0.041 0.000
Vb 0.317 -0.111 -0.123
0.088 0.558 0.518
Vd 0.274 -0.257 -0.196 0.865
0.142 0.170 0.299 0.000
Vc 0.308 -0.174 -0.183 0.945 0.917
0.098 0.357 0.333 0.000 0.000
Fb 0.208 -0.431 -0.322 0.169 0.548
0.271 0.018 0.083 0.373 0.002
11 | P a g e
Fd 0.062 -0.299 -0.243 -0.163 0.107
0.745 0.109 0.195 0.390 0.574
Fc 0.239 -0.464 -0.325 0.298 0.642
0.203 0.010 0.079 0.110 0.000
Vc Fb Fd
Fb 0.315
0.090
Fd -0.004 0.752
0.983 0.000
Fc 0.452 0.964 0.753
0.012 0.000 0.000
Cell Contents: Pearson correlation
P-Value
1. Vm (-0.337, P-Value = 0.068):
o There is a moderate negative correlation between Vm and the Design Point.
As Vm increases, the Design Point tends to decrease slightly.
o The P-Value is 0.068, which is marginally above 0.05, meaning this
correlation is not quite statistically significant but is close to being so.
2. Vmc (-0.376, P-Value = 0.041):
o There is a moderate negative correlation between Vmc and Design Point.
o The P-Value is 0.041, indicating this correlation is statistically significant at
the 5% level. Thus, there is enough evidence to suggest that as Vmc
increases, the Design Point tends to decrease.
3. Vb (0.317, P-Value = 0.088):
o There is a moderate positive correlation between Vb and Design Point,
meaning as Vb increases, the Design Point tends to increase as well.
o However, the P-Value is 0.088, indicating that this relationship is not
statistically significant.
4. Vd (0.274, P-Value = 0.142):
o There is a weak positive correlation between Vd and Design Point, but this
correlation is not statistically significant (P-Value = 0.142).
5. Vc (0.308, P-Value = 0.098):
o There is a moderate positive correlation between Vc and Design Point.
o However, with a P-Value of 0.098, this correlation is not statistically
12 | P a g e
significant at the 5% level.
6. Fb (0.208, P-Value = 0.271):
o There is a weak positive correlation between Fb and Design Point.
o The P-Value of 0.271 indicates that this correlation is not statistically
significant.
7. Fd (0.062, P-Value = 0.745):
o The correlation between Fd and Design Point is very close to 0, indicating
almost no linear relationship between these variables.
o The P-Value of 0.745 shows that this correlation is not statistically
significant.
8. Fc (0.239, P-Value = 0.203):
o There is a weak positive correlation between Fc and Design Point.
o The P-Value of 0.203 indicates this relationship is not statistically significant.
Significant Correlation: Only Vmc has a statistically significant correlation with the
Design Point (negative correlation).
Non-significant Correlations: Other variables like Vm, Vb, Vd, Vc, Fb, Fd, and Fc
have weak to moderate correlations with the Design Point, but none are statistically
significant.
13 | P a g e
