9 Tests Summary Table:

No Type Steps Remark

Descriptive Analyze -> Descriptive Statistics -->

1 Frequency Frequency

Analyze -> Descriptive Statistics -->

2 Cross Tabulation Cross Tab

Transform -> Recode into different Create categories based on random

3 Data Category variables data

4 Reliability test Analyze -> Scale --> Reliability Cronbach alpha (variable & item)
Data Transform items in variable to
5 Transformation Transform --> Compute mean

6 Correlation Analyze--> Correlate --> Bivariate Relationship between 2 variables

To check influence between
7 Regression Analyze --> Regression --> Linear variables
Compare Means --> One-Way Compare Significant difference
8 t-test & ANOVA ANOVA based on mean

9 Forecasting Forecasting --> Create Models Predict outcome

1
1. Descriptive Frequency:

a. SPSS Steps:

b. Output:

2. Cross Tabulation:

a. SPSS Steps:

b. Output:

2
The test allows statistical calculation of different demographics:

3. Data Category:

*Pending

3
4. Reliability Test:

c. SPSS Steps:

1. Click Analyze  Scale  Reliability Analysis

2. Choose the “items” belonging to the specific “variable” to test

reliability

Choose IVs and DV separately

3. Tick on “Item” and “Scale if item deleted”

d. Output:
1. Reliability of the “Variable” (Either IV or DV)

2. Reliability of each “item” inside the “variable)

4
 e. Interpretation:

Scale:

0-0.5 Low
0.5-0.6 medium
0.6-1.0 High

 Above 0.5 is expected to have higher reliability

 Each time, run the reliability test on “items” belonging to 1 “variable”
 Items that failed reliability can be opted to be removed from the final study assuming it as an
error

f. Report:

The reporting format shall follow as per below table:

Alpha Alpha
Variable Result Item Result Remark
1
2
3
X 4
1
2
3
Y 4

g. Practical Implication/ Theory:

1. Relibility test attempts to answer following concerns:

 The right sample was chosen
 Respondents have clear understanding of the questions
 The survey was conducted at a suitable time
 The items/ variable are reliable to deduce the hypothesis

5
5. Data Transformation

a. SPSS Steps:
1. Click Transform  Compute Variable

2. Name the Target Variable. The output will be

displayed in a new column in the “Data View”
Section

3. Compute the “mean” for each IV and DV

4. Mean = (Q1 +Q2 +Qn) / n

b. Output:

The mean for each IV/DV of that particular respondent will be available:

6
c. Interpretation:

1. Lykert scale represented in following table:

Lykert Scale Points

Strongly Disagree 1
Disagree 2
Neutral 3
Agree 4
Strongly Agree 5

2. The mean result should be checked based on the point system of Lykert Scale

d. Practical Implication/ Theory:

1. Data transformation creates the mean/average for variables based on each items
2. It means the mean of respondent N’s answer to questions within a variable
3. The mean shall be evaluated based on the point scale of the Lykert scale system

7
6. Correlations

a. SPSS Steps:
1. Click Analyze Bivariate

2. Choose the IVs and DVs to test correlation

3. Choose to output mean and standard

deviation from the “options”

8
 b. Output:

Result based on Pearson Correlation and Significant Test:

c. Interpretation:

1. Pearson correlation has a scale ranging from -1 to +1

2. There are 4 types of relationship that can be deduced as follow:
a. Close to 1 – Strong relationship between variables. Changes in 1 variable strongly
correlated changes in second variable
b. Close to 0 – Weak relationship between variable.
c. Positive (+) – Increase in 1 variable causes increase in another. Similarly when
decrease
d. Negative (-1) – Increase in value in 1 variable causes decrease in another variable

3. There are 2 output for sig (2-tailed) test:

a. > 0.5 – No significant correlation
b. <0.5 – Statistically significant correlation

9
 4. The scaling for pearson correlation as below:

Relationship
Value
-1
-0.6 to -1 High POSITIVE
-0.5 to -0.6 Moderate
0 - (-.5) Low
0
0 - (.5) Low
0.5 to 0.6 Moderate NEGATIVE
0.6 to 1 High
1

d. Report:

Transform the correlations table to a reporting table:

X1 X2 X3 Y
X1 - 0.508 0.514 0.472
X2 - 0.659 0.564
X3 - 0.622
Y -

*There is strong positive relationship between variables X2 and X3

e. Practical Implication/ Theory:

1. Correlations allow to examine the symptoms of variables

10
7. Regression:

a. SPSS Steps:
1. Click Analyze Regression  Linear

2. Choose the IV (one first) and DV

3. Choose all options

b. Output:
The result is based on output given in the modal summary and coefficient table:

11
c. Interpretation:

1. The “Adjusted R Square” value denotes the influence of IV towards DV

2. The result should be multiplied by 100%
3. After finished establishing the “Adjusted R Square” for each IV on the DV, proceed with multiple
regression to understand the influence of IVs on DV
4. The scaling for regression is as below:

Value Influence
0 - (50%) Low
50% to 60% Moderate
60% to 100% High

5. The output on coefficient table  Significant denotes the significance and judged by following
scale:

Value Result
0.05 – 0.001 insignificant
0 significant
-0.05 – (-0.001) non significant
6. Lastly, the outputs allow to develop the equation to represent the research:

Y = a + bX

Y – Dependent Variable

X – Independent Variable

a- Constant
b- Coefficient

12
d. Report:

1. Firstly establish the “Adjusted R Square” value for each IV. Then, proceed with multiple IV.
Develop the table as below:

Variable Y Y
X1 21.90%
X2 31.50% 43.70%
X3 38.30%

2. The regression equation is based on the formula, Y= a + Xb

e. Practical Implication/ Theory:

1. Linear regression provide an in-sight on which variable to prioritize

2. Multiple regression provides an in-sight on the influence of the group to the output

13
8. ANNOVA

a. SPSS Steps:

1. Click Analyze Compare Means 

One-Way ANOVA

2. Choose the IV and DV

3. Choose settings:

a. Post-Hoc LSD
b. Options  Means Plot

14
b. Output:

These are outputs concerning ANOVA test:

15
 c. Interpretation:

1. The table represents the significant difference between independent variables based on scale
below:

Value Meaning
0.05 insignificant
0 significant
-0.05 non significant

2. A value closer to “0” means that there significant difference between the independent variables
on the output.
3. The mean plot illustrates the output in a graphical manner

d. Practical Implication/ Theory:

1. Understanding the significant difference between IV that influences the output allows easier
decision making on choosing the suitable IV.

16
9. Forecasting

a. SPSS Steps:
1. Click Analyze Forecasting  Create
Models

2. Choose the IV and DV

3. Choose settings:

c. Statistics Parameter Estimates + Display

Forecasts
d. Specified Year & Month

17
 b. Output:

Forecasting table and graph will be displayed:

c. Interpretation:

1. The forecasted output is displayed for the upcoming months/years

d. Practical Implication/ Theory:

1. The result allows predicting the outcome so that appropriate measures can be taken to
minimize the risk of failure to achieve target

18