CORRELATION ANALYSIS USING SPSS

In this post, I am going to tell you how to run simple correlation analysis using SPSS. Let’s illustrate this with an example. Imagine, you are conducting a survey and collecting data on the following matters of respondents.

1. Gender

2. Age

3. Income in Dollars ($$)

4. Brand Loyalty (Perceived)

5. Service Quality (Experienced/Perceived)

First of all, you need to input the above mentioned variables in to SPSS. For details on how to enter/ input the variables in the SPSS please see my previous posts. Once, the variables and values are entered, now you are ready to enter the data. And once the data is entered in SPSS Data View window, now you are ready to run preliminary tests such as descriptive statistics (Previous posts) or Correlation Analysis (Discussed in this post)

In this example, the variable of Brand Loyalty is entered via likert scale with 1 refers to very low brand loyalty, 2 refers to low, 3 refers to neutral, 4 refers to high, and 5 refers to very high brand loyalty. The variable of service quality is also based on likert scale with 1 refers to very poor service quality, 2 refers to poor, 3 refers to neutral, 4 refers to good, and 5 refers to very good service quality. Since, correlation analysis is mostly run when data is continuous (based on likert scale); therefore, the data qualify for running normal correlation analysis.

The command for running correlation analysis is as under.

Analyze--- Correlate---Bivariate

Now select the variables which you want to correlate and move them to the selection window, and then Press OK. Results will appear.

The results will appear in table form with the heading of correlations. The interpretation is that if you go by column, you will see that in the first column there are different details but mainly the both variables with heading Pearson correlation, sig (2 tailed), and N for both variables. If we go by row, then first for brand loyalty, the value of Pearson correlation of .431 in third column shows that there is 43.1% association between brand loyalty and service quality. Moreover, the relationship between both variables is also significant since the value of sig (2-tailed) refers to the significance or P value and is slightly bigger than 0.05. The N shows the size of sample, which in this case is 20 meaning there were twenty respondents participated in this survey. 

Moving to the next row, you will also get almost same result but only with different position. This means that if you want to see the relationship between service quality and brand loyalty, so this is also 43.1% association between both variables. Moreover, the relationship is significant (p value <0.05) and N means sample size is also 20. The results for both variables is so same because actually, both results are one. Reason, if you compare potato with tomato, or tomato with potato, you will certainly get the same result. Hence, in correlation analysis, the value of correlation between any two variables comes twice but the value remains same.

Correlation between More Than Two Variables (Multiple Variable Correlation):

Lets assume that you run the correlation with same procedure as mentioned above with the exception that you entered three variables in correlation instead of two. The variables which you entered are Income, brand loyalty, and service quality. You will get new results.

Here in this new result table, let’s go with comparing brand loyalty with service quality and income. Going through the first row, the value of .431 shows that there is 43.1% association between brand loyalty and relationship is significant (p value=0.058). Similarly, the value of .351 in income column shows that the brand loyalty and income has 35.1% association while the relationship is insignificant (p value is greater than 0.05). Similarly, you can go to second row and see the relationship between service quality and other two variables, and same procedure for third row with income.

Note: 

1. you can add more than two variables and can get reasonable results up to 10 to 15 variables. 

2. Significant value of P should be less than 0.10 to be moderate significant, less than 0.05 to be significant, and less than 0.01 to be highly significant.

Sample Example SPSS file is as under.
Sample SPSS Practice File

For details on Online Classes for SPSS at economical fee, contact the following:

Email: onlinetrainingsolution@gmail.com

Skype Id: faireast1

Mobile: +92-3239256994
Facebook Page: Online Training Solution
Facebook Page Link

Thank You