Using Exploratory Factor Analysis (EFA) Test in Research
This easy tutorial will show you how to run the exploratory factor analysis test in SPSS, and how to interpret the result.
The purpose of an EFA is to describe a multidimensional data set using fewer variables. Once a questionnaire has been validated, another process called Confirmatory Factor Analysis can be used. This is supported by AMOS, a ‘sister’ package to SPSS. (Source)
EFA has two goals:
- Identification and understanding of the basic idea
- Reducing the number of variables in an analysis when there are too many, some of which overlap because they have similar meanings and behavior.
Assumptions of exploratory factor analysis:
- Sample size (N > 150)
- Eligibility of correlation matrix for factorization
- No outliers
An Example: How to run exploratory factor analysis test in SPSS
We collected data from students about their feeling before the exam. The students were asked to rate the following feelings on the scale from 1 to 5. We wanted to reduce the number of variables and group them into factors, so we used the factor analysis.
Before starting the Analysis: The Approach
- Before carrying out an EFA the values of the bivariate correlation matrix of all items should be analyzed. It is easier to do this in Excel or SPSS. High values are an indication of multicollinearity, although they are not a necessary condition. Suggests removing one of a pair of items with bivariate correlation scores greater than 0.8.
- Decide on the appropriate method and rotation (probably varimax to start with) and run the analysis.
- Remove any items with communalities less than 0.2 and re-run.
- Optimize the number of factors – the default number in SPSS is given by Kaiser’s criterion (eigenvalue >1) which often tends to be too high. You are looking for as many factors as possible with at least 3 items with a loading greater than 0.4 and a low cross-loading as a result fix the number of factors to extract and re-run.
- Clear away any items with no factor loadings > 0.3 and you need to perform the test again.
- Remove any items with cross-loadings > 75% starting with the one with the lowest absolute maximum loading on all the factors.
- Once the solution has stabilized, check the average within and between factor correlations. To obtain the factors, use a PCA with the identified items and save the regression scores Hence, If there is not an acceptable difference between the within and between factor average correlations, for the reason that you should try an oblique rotation instead.
A number of final checks;
8. Provided the average within factor correlation is now higher than the average between factor correlation, a number of final checks should be made:
- Check that the proportion of the total variance explained by the retained factors is at least 50%.
- Control the adequacy of the sample size using the KMO statistic and a minimum acceptable score for this test is 0.5
- If the sample size is less than 300 check the average commonality of the retained items. Therefore an average value above 0.6 is acceptable for samples less than 100 likewise an average value between 0.5 and 0.6 is acceptable for sample sizes between 100 and 200.
- The determinant of the correlation matrix should be greater than 0.00001 due to a lower score might indicate that groups of three or more questions have high intercorrelations, so the threshold for item removal should be reduced until this condition is satisfied.
- Cronbach’s alpha coefficient for each scale can also be calculated.
- If the goal of the analysis is to create scales of unique items then the meaning of the group of unique items that load on each factor should be interpreted to give each factor a meaningful name. (Source)
This guide will explain, step by step, how to run the exploratory factor analysis test in SPSS statistical software by using an example.