Diversity and Inclusion Survey Analysis 19th Sep
Diversity and Inclusion Survey Analysis 19th Sep
and Inclusion Survey Analysis
Variables and data table:
Transforming the qualitative data to quantitative using the following:
Data File
Questioner
Response No. Y X1 X2 X3 X4 X5 X7 X8
1 4.60 4.57 5.00 3.00 5.00 4.33 5.00 3.00
2 4.40 4.86 5.00 3.67 5.00 4.67 5.00 5.00
3 3.80 3.57 4.00 4.33 3.50 3.33 4.00 3.00
4 5.00 5.00 5.00 5.00 5.00 5.00 5.00 5.00
5 4.20 4.57 5.00 4.33 3.00 4.00 4.00 5.00
6 5.00 5.00 5.00 4.33 5.00 5.00 5.00 5.00
7 4.00 4.57 5.00 4.00 4.00 5.00 5.00 4.00
8 4.20 4.14 4.50 4.00 5.00 4.67 4.00 5.00
9 4.20 4.14 4.50 3.33 4.50 4.00 4.00 3.00
10 3.20 3.71 3.50 3.67 4.00 4.00 3.00 4.00
11 4.00 4.57 4.00 4.00 4.00 4.00 5.00 5.00
12 4.40 4.14 3.50 4.00 5.00 3.67 4.00 4.00
13 3.60 3.86 2.50 4.00 4.00 3.00 4.00 3.00
14 4.00 4.00 4.00 3.67 4.00 4.00 5.00 4.00
15 5.00 5.00 5.00 5.00 5.00 5.00 5.00 5.00
16 4.00 4.43 4.00 4.00 5.00 4.00 5.00 4.00
17 4.60 4.29 5.00 2.33 5.00 3.67 4.00 5.00
18 4.00 4.00 4.50 4.00 4.50 4.33 4.50 4.00
19 5.00 4.14 4.00 5.00 5.00 5.00 5.00 5.00
20 4.60 4.71 4.50 4.67 4.00 3.33 5.00 5.00
21 3.00 4.14 4.50 3.00 4.00 3.67 3.50 5.00
22 3.40 4.00 3.50 3.67 4.00 4.00 4.00 3.00
23 3.60 2.86 2.50 2.67 3.50 3.67 4.00 2.00
24 4.00 4.14 4.00 4.00 4.00 4.67 5.00 4.00
25 4.60 4.71 5.00 4.33 4.50 4.33 4.00 5.00
26 4.40 4.71 4.50 3.67 5.00 5.00 5.00 4.00
27 3.00 3.14 4.00 3.00 4.00 3.67 4.00 3.00
28 0.00 5.00 4.00 3.67 0.00 0.00 0.00 0.00
29 4.00 3.14 3.50 3.67 4.00 4.00 4.00 4.00
30 4.40 4.43 3.50 3.33 5.00 5.00 4.00 3.00
31 2.80 3.86 3.50 3.00 4.00 4.00 4.00 4.00
32 3.80 4.00 4.00 3.00 4.00 4.67 4.50 5.00
33 4.00 3.86 4.00 2.67 3.50 5.00 5.00 5.00
34 4.20 4.57 4.00 4.33 4.50 4.67 4.00 5.00
35 0.00 4.00 2.00 2.33 4.00 4.00 2.50 5.00
36 4.20 4.57 5.00 2.67 4.00 5.00 5.00 4.00
37 4.00 4.00 4.00 4.00 4.00 4.00 4.00 4.00
38 3.20 3.71 4.00 2.67 3.00 4.00 4.00 4.00
39 4.00 4.14 4.00 3.67 4.00 4.00 4.00 4.00
40 3.00 4.00 3.00 2.00 3.00 2.00 2.00 3.00
41 3.60 3.71 4.00 2.33 4.00 4.00 4.00 4.00
42 4.60 4.57 5.00 4.67 5.00 5.00 4.00 5.00
43 4.60 4.43 4.50 4.67 4.50 4.67 4.50 5.00
44 5.00 5.00 5.00 3.33 5.00 5.00 4.00 5.00
45 4.20 4.43 5.00 5.00 5.00 5.00 5.00 4.00
46 3.40 3.86 4.00 3.00 4.00 3.67 4.00 3.00
47 4.40 4.57 4.50 4.33 4.50 4.33 5.00 5.00
48 3.40 3.43 3.00 2.33 4.00 4.67 4.00 4.00
49 3.80 4.29 4.00 3.00 4.50 4.33 4.00 4.00
50 4.00 5.00 4.00 4.33 4.00 4.67 4.00 4.00
51 4.00 4.00 4.00 3.00 4.50 4.00 4.00 5.00
Correlation Examination:
ꝭ
This is to check if there is significant correlation between Y variable and each of the independent variables ( Y,X1
ꝭ ꝭ ꝭ ꝭ ꝭ ꝭ
‐ Y,X2 ‐ Y,X3 ‐ Y,X4 ‐ Y,X5 ‐ Y,X7 ‐ Y,X8) ‐ From E‐views we could have the correlation value at level of
sample (r) and its probability (P value) the following Hypothesis have been performed on each of population
correlation:
ꝭ
Null ‐ Ho: Y,X1 = 0 (There is no significant Correlation between Y and X1) ‐ In case of accepting Null, we must
exclude X1 from independent variables
ꝭ
Alternative‐ H1: Y,X1 ≠ 0 (There is significant Correlation between Y and X1) ‐ In case of accepting Alternative,
we must keep X1 in independent variables.
Correlation
Probability Y X1 X2 X3 X4 X5 X7
Y 1.000000
-----
X1 0.299903
0.0325
1.000000
-----
ꝭ
Pvalue (t) to test Y,X1 ≠ 0 ‐
Exclude X1 if equal 0
X2 0.588046 0.645905 1.000000
0.0000 0.0000 -----
ꝭ
Hypothesis of Y,X1:
ꝭ ꝭ
Null – Ho : Y,X1 = 0 (No significant Correlation) ‐ ‐ ‐ Alternative H1 : Y,X1 ≠ 0 (Significant Correlation
Assuming confidence interval 95%, α = 0.05, α/2 = 0.025
Testing Y, X1: Since Pvalue = 0.0325 > α/2 (0.0250) then the null is
acceptable, and alternative is rejected.
Testing Y, X2: Since Pvalue = 0.0000 < α/2 (0.0250) then the null is rejected,
and alternative is acceptable
Testing Y, X3: Since Pvalue = 0.0007 < α/2 (0.0250) then the null is rejected, α/2
α/2
and alternative is acceptable
Testing Y, X4: Since Pvalue = 0.00000 < α/2 (0.0250) then the null is
rejected, and alternative is acceptable
Testing Y, X5: Since Pvalue = 0.00000 < α/2 (0.0250) then the null is
rejected, and alternative is acceptable
Testing Y, X7: Since Pvalue = 0.00000 < α/2 (0.0250) then the null is
rejected, and alternative is acceptable
As a result of that, X1 variable has significant linear significant correlation
with the dependent variable. However all other independent variables
do not have, so will be excluded
In addition to the correlation, test that resulted X1 variable only. It is obvious that Variable X1 has significant
correlation with Variables X4, X5, and X7 .
From Eviews, the model so far is as follow (using independent variable of X1 only:
Dependent Variable: Y
Method: Least Squares
Date: 09/14/21 Time: 11:03
Sample: 1 51
Included observations: 51
Pvalue ‐ (F) to test model goodness
Testing Goodness of model:
Hypothesis of Goodness:
Null – Ho : β1 = 0 (No significant Coefficient values – Not good model) –
Alternative H1 : At least one of the coefficients has significant value (Good model)
Assuming confidence interval 95%, α = 0.05,
Since Pvalue (F) = 0.032506 < α (0.05) then the null is rejected, and
alternative is acceptable.
As a result of that, variable coefficient haS significant value that
means Model is good
The Good Model is:
Testing the model is good only or good and best?
From the above Eviews equation result, we will test the hypothesis of the variable coefficient if having significant value or not,
by which we can exclude the variables of non-significant coefficient value to obtain the best model.
Testing best model:
Hypothesis of Best Model:
Null – Ho : β1 = 0 (No significant Coefficient value – if acceptable, exclude X1 from model)
Alternative H1: β1 ≠ 0 (Significant Coefficient value – if acceptable, keep X1 in model)
Assuming confidence interval 95%, α = 0.05, α/2 = 0.025
Since Pvalue of X1 variable coefficients is 0.0038 < α/2 (0.0250) then
the null is rejected, and alternative is acceptable.
Since Pvalue of X1 variable coefficients is 0.0325> α/2 (0.0250) then
the null is accepted, and alternative is rejected
As a result of that with X1, model is not the best
α/2 α/2
Testing of Heteroskedasticity in model:
Using Eviews for Heteroskedasticity in the best model, resulted the following resulted:
Hypothesis of Hetero:
Null – Ho : Homo. (Model does not suffer from Hetero) –
Alternative H1 : Hetero. (Model suffers from Hetero)
Assuming confidence interval 95%, α = 0.05,
Since Pvalue (F) = 0.3325 > α (0.05) then the null is acceptable, and
alternative is rejected.
As a result of that, the best model does not suffer from
Heteroscedasticity.
H1 Acceptable
Ho Acceptable
Pvalue ≤ α
Pvalue > α
Testing of Auto‐Correlation in model:
Using Eviews for Auto‐correlation in the best model with lag of 1, resulted the following result:
Hypothesis of Auto‐correlation:
Null – Ho : No auto‐correlation
Alternative H1 : Model suffers from auto‐correlation
Assuming confidence interval 95%, α = 0.05,
Since Pvalue (F) = 0.8447 > α (0.05) then the null is accepted, and
alternative is rejected.
As a result of that, the best model does not suffer from auto‐
correlation
Ho Acceptable H1 Acceptable
Pvalue > α Pvalue ≤ α
So, Based on the above, the good Model of the relation between the Inclusion and all other surveyed factors
indicates that the most effective factor on the Inclusion is the Diversity and Inclusion Culture in the
Organization governed by the following Equation:
Given, X1 = 5 (100%)
Substituting in the latest model,
Y = 1.471392 + 0.572242 (X1)
Given, X1 = 1 (20%)
Y = 2.043634 = (41%)