INTRODUCTION
Statistical Package for Social Sciences (SPSS) is one of the most
popular data analyses software packages used by academics. It use cuts across
all social sciences based disciplines hence, it important for all researchers
to understand how to use this great tool. SPSS is used for the analyses data employing
statistical methods like:
1) Simple and Multiple Regression Analyses; 2) Correlation Analyses;
(Part, Partial, Bi-variate, Multivariate etc);
3) Analyses of Variance; 4)
Analyses of Co-Variance; 5) Neural
Networks; and so many others we may not be able to detail here.
This article is designed to show you how to use this great statistical
package to perform Pearson Correlation Analysis. Finally, the article will also
show you how to interpret your results.
Pearson Correlation Analysis is a statistical Technique for Measuring
the strength of association –relationship -correlation between variables in a
research
The first step in performing an analyses be it regression or
correlation analysis is to open the software user interface. We assume of
course that you have and understand the basics of your data-set. For example,
we assume that you understand the difference between dependent and independent
variables and have also been able to identify this in your data set. When you
open the user interface of SPSS from its icon on your computer, you should see
a screen like the one here:]
This is the first screen that you see when you open the software every
time you want to use it. What you should do is to close the smaller inset
window from the button indicated by the red circle. From the window now
remaining you can now start your analysis.
Running Your Analysis
Now enter your data as shown here
- dependent variable in the first column and independent variable in the
second column (please ensure that the data view is selected at the bottom left
of the screen circled in red).
Note that in a Pearson Correlation, identifying and entering data on
the basis of dependent and independent variable is not a pre-requisite in
performing the analysis as the results of correlation are in most cases 2 way
in nature.
If you already have your data in another spreadsheet program like MS Excel
just copy and paste your data. When you are done entering your data, click on
the variable view close to the circled data view at the bottom left of the
screen. This will give the window below:
The first column captioned ‘Name’, is by default filled in the first
two rows with VAR00001, VAR00002 and VAR00003 given the number of
variables. For clarity sake, we give
them the hypothetical names GDP and FDI and DI.
Please note that spaces are not allowed in renaming any of the
variables.
When you are done with the renaming, please go back to the data view
and observe that the columns with data has been re-captioned GDP and FDI from
VAR00001 and VAR0002 like it is shown below:
Now you are ready to perform the actual analyses and as the name
implies, find the tab at the top named: Analyze and click on it as shown below:
When you click on the highlighted 'Bivariate' Tab, the screen below
will appear:
If you'd rather perform a part and partial correlation, then click on
the next Tab after Bivariate.
From the Window shown above, select the variables shown on the left
hand box and move them to the right hand side.
You can also choose to work with only some of the variables on a piece
meal basis in which case you should choose the necessary ones and move to the
next box.
Next, Tick the Pearson button if it is not already selected.
Next select Two-Tailed or One-Tailed test depending on the nature and
direction of your hypotheses.
Also ensure that the 'Flag Significant Correlation button is
selected'.
Next click on the 'Options' Tab on the top right hand corner of the
Box and select the 'Means and Standard Deviation' option.
When you are done, now click on 'OK’ at the bottom of the screen like
so ....
Now you have performed your first Pearson Correlation using SPSS -
CONGRATULATIONS!
Specimen Output
Here is a specimen of the result output:
Follow these steps to copy your result to a word document:
From the output screen shown, click on 'Edit', Scroll down and click
on ‘Select all’. Now the entire result output is selected, go back and click on
'Edit' again but this time select 'Copy', wait a moment, now open a word
document and paste your result.
Now, observe that the the results displays 2 different tables. One
captioned 'Descriptive Statistics' and the other 'Correlation'.
As the name implies, the first table describes the features or
characteristics of your data set. The Mean, Standard Deviation and Sample size
(N) for each of the variables.
The second table captioned 'Correlations' is the most important of the
2 tables because here we can actually see and interpret the two-way
relationships (Correlations) between the variables of the study.
The Table is broadly divided into three rows tagged GDP, FDI and DI.
Each of these rows is further divided into three rows namely Pearson Correlation,
Sig (2-tailed) and N.
The first sub-row in the first row is the show the correlation between
GDP, FDI and DI. If you look carefully, you will notice that the content of the
first broad row is the same as the second and the third but arranged differently.
Hopefully, you have a basic knowledge of the matrix because that is
what the table is called - (Correlation Matrix) and that also explains the
repetition of the contents.
The point here is that in your interpretation of the contents, you do not
need to go beyond that first broad row as clearly marked by the red circle.
In the second column captioned GDP, the first row give a value of 1.
This value is the correlation on GDP on itself which is why it gives the value
of 1 indicating a perfect correlation. You probably will not need that value in
your interpretation.
The first value in column three under FDI show the correlation between
GDP and FDI and gives a value of -.552. This value indicates a negative
correlation between GDP and FDI of 55.2 percent. This implies that an upward
movement in FDI will lead to a downward movement in GDP. On the other hand, a
downward movement in FDI will lead to an upward movement in GDP. That is an
inverse relationship between GDp and FDI.
In the last column (DI), the first row gives the correlation between
GDP and DI. the value is indicated to be 1.000 which implies a perfect
correlation between GDP ans DI. This means that movement in any of the two
variables in any direction will be accompanied by movement in the other
variable in the same direction and in the same proportion.
Also note the two correlation values for FDI and DI are marked with
double stars (**) indicating a significant relationship between the variable at
0.01 level.
The second row (Sig.) show outputs under FDI and DI only. The values
shown are 0.000 for FDI and 0.000 for DI which indicate that both are highly
significant 99 percent level.
Final row (N) shows values of 37 in all columns indicating that the
sample size is 37 observations in all variables.
On a final note, we observe that the null hypotheses in both cases is
rejected hence, we conclude that there FDI and DI significantly affect/impact
GDP.
We appreciate your comments and observations, please use the comment box below or Email optistrat.info@gmail.com
Go to Homepage to view a list of our well researched, fully supervised and approved Accounting and Banking and Finance Project Topics and Materials.
Go to Homepage to view a list of our well researched, fully supervised and approved Accounting and Banking and Finance Project Topics and Materials.
No comments:
Post a Comment