Factor analysis, also known as principle component analysis (PCA), can be used to condense a large number of variables into a smaller set of factors while still retaining core information. This method is typically used in situations where the large number of input variables is too difficult to analyze as-is.
Run Factor Analysis
- Input the number of factors you would like to use. We recommend utilizing a scree plot or setting your factors with eigen values.
- Select rotation, note that at this point in time we only have the option to do an orthogonal rotation or no rotation.
- Select the variables of interest and select Run.
Factor Analysis Output
In the results, "uniqueness" is the proportion of that variable which cannot be predicted from the other variables in the analysis. Factor loadings for each factor are also given for your variables, along with the sum of squares, proportion of variance, and cumulative variance. The chi-squared analysis at the bottom of the output is testing the hypothesis that the model fits the data perfectly.