Exploratory Factor Analysis

Exploratory Factor Analysis is a data reduction technique that is used to put together strongly linked variables into an associated set called a factor.

Assumptions for conducting EFA

1.       Multiple variables measured at either ordinal or interval scale. (Most commonly used is 5 point likert scale)
2.       Linear relationship between variables.
3.       Variables should be adequately correlated.
4.       There is need for sample adequacy i.e. rule of thumb says for ‘X’ number of variables under study, data should be collected                  from X*5 respondents (i.e. 5 times the variables under study).

Performing Exploratory Factor Analysis using SPSS

1. Open the SPSS file where you have entered the data to perform Exploratory Factor Analysis.
2. In the File menu click -  Analyze > Dimension Reduction > Factor
_

3. Select all variables for which you want to perform factor analysis and transfer them to the right side variable window.

4. Select ‘Descriptives’ option and choose option for KMO and Bartlett’s test of Sphericity. Click on continue.

5. Select ‘Extraction’ option and choose scree plot option. Click on continue.

6. Select ‘Rotation’ option and choose Varimax (most commonly used rotation method on social sciences). Varimax rotation which is orthogonal in nature is applied to maximizing the variance of the squared loadings of a factor on all the variables in a factor matrix. In Varimax rotation each original variable tends to be associated with one of factors, and each factor represents only a small number of variables leading to simplification of interpretation of results. Click on continue.

7. In ‘Options’ choose sorted by size and suppress small coefficients. Put a value of 0.4 in the space asking for ‘Absolute value below’. Click on continue.

8. Click on ‘OK’
9. Output window will appear.