A data scientist runs PROC FACTOR with METHOD=PRINCIPAL ROTATE=VARIMAX on a 20-variable dataset. What is the purpose of ROTATE=VARIMAX?
Select an answer to reveal the explanation.
Short Explanation
You use ROTATE=VARIMAX to rotate the factor solution so each factor gets a clearer pattern of loadings. It pushes loadings toward 0 or 1 by maximizing the variance of squared loadings within each factor, making the factors easier to interpret.
Full Explanation
The correct option says it rotates the factor solution to maximize the variance of squared loadings within each factor, making factors more interpretable. Varimax rotation is an orthogonal rotation that maximizes the variance of squared loadings within each factor column, driving loadings toward 0 or 1 and making each variable load strongly on as few factors as possible, which aids interpretability. Sorting the factor loading matrix by decreasing eigenvalue is wrong because rotation does not sort eigenvalues. Applying a varimax normalization to the raw data before factoring is wrong because Varimax operates on the loading matrix, not raw data. Removing factors with eigenvalues below 1 is wrong because Kaiser criterion uses MINEIGEN=, not ROTATE=VARIMAX.