Orthogonal rotation in factor analysis:

Orthogonal rotation in factor analysis:

• A. A rotation that makes factors perfectly correlated
• B. A rotation that collapses all factors into a single dimension
• C. A rotation that changes the number of factors extracted
• D. Keeps the underlying factors independent (uncorrelated)

Answer: (D)

Orthogonal rotation aims to make the interpretation of factors easier while keeping them independent. After you extract factors, you rotate the factor axes to achieve a simpler, more interpretable pattern of loadings. When the rotation is orthogonal, the axes stay at right angles, which means the factors remain uncorrelated with each other. This preservation of independence helps you see which variables clearly group together on each factor without introducing correlations between factors. In practice, the goal is a simple structure: each variable loads highly on one factor and only weakly on others. Orthogonal rotations like Varimax accomplish this without changing how many factors you’ve extracted or the overall amount of variance the factors explain; they only reorient the axes. That’s why this option best fits orthogonal rotation: it keeps the underlying factors uncorrelated. It does not imply perfect correlation, it does not collapse factors into a single dimension, and it does not change the number of factors extracted.

Orthogonal rotation aims to make the interpretation of factors easier while keeping them independent. After you extract factors, you rotate the factor axes to achieve a simpler, more interpretable pattern of loadings. When the rotation is orthogonal, the axes stay at right angles, which means the factors remain uncorrelated with each other. This preservation of independence helps you see which variables clearly group together on each factor without introducing correlations between factors.

In practice, the goal is a simple structure: each variable loads highly on one factor and only weakly on others. Orthogonal rotations like Varimax accomplish this without changing how many factors you’ve extracted or the overall amount of variance the factors explain; they only reorient the axes.

That’s why this option best fits orthogonal rotation: it keeps the underlying factors uncorrelated. It does not imply perfect correlation, it does not collapse factors into a single dimension, and it does not change the number of factors extracted.