In this article
Factor analysis is an approach to describing, if possible, the covariance relationships among many variables in terms of a few underlying, but unobservable, random quantities called factors.
Factor analysis is a variable reduction procedure. It is useful when you have obtained data on a number of variables (possibly a large number of variables), and believe that there is some redundancy in those variables. In this case, redundancy means that some of the variables are correlated with one another, possibly because they are measuring the same construct. Because of this redundancy, you believe that it should be possible to reduce the observed variables into a smaller number of underlying factors (artificial variables) that will account for most of the variance in the observed variables.
The actual meaning of these underlying factors is up to the analyst to interpret, based on the variables included in the factor.
Note: Loop questions cannot be used in factor analysis.
Constraints
Factor Analysis calculations can only be performed based on variables which contain a numeric measurement. Thus only the following questions can be used: Numeric, Numeric list answers, Singles with all numerical codes/scale, and Grid answers with all numerical codes/scale. Note that Grid and Numeric List questions can be dropped onto the variables field, but will be expanded to the corresponding grid/list answer questions.
Only filters of type Filter Expression are supported in Factor Analysis calculations.
Principal component analysis is a large-sample procedure. To obtain reliable results, the minimum number of subjects providing usable data for the analysis should be the larger of 100 subjects or five times the number of variables being analyzed.