Which statistical technique is used to identify underlying dimensions by clustering related items?

• A. Factor analysis
• B. Regression
• C. Time-series analysis
• D. Chi-square test

Answer: (A)

Identifying underlying dimensions from a set of observed items is what factor analysis does. It examines how items correlate with one another and groups them into a smaller number of latent factors, each representing a dimension that influences responses. Items that load strongly on the same factor tend to measure the same underlying construct, so factor analysis reveals the hidden structure that explains why certain questions cluster together. This is especially useful when you’re trying to capture broad traits or dimensions in areas like personality, motivation, or emotion. By uncovering these latent constructs, you can interpret how different items relate to core dimensions rather than treating each item in isolation. In contrast, regression predicts an outcome from predictors, time-series analyzes data over time to detect patterns, and chi-square tests look at relationships or goodness-of-fit for categorical data, not the latent structure behind a set of items. Note that while methods like principal components analysis also reduce data, factor analysis specifically targets the latent constructs that give rise to the observed correlations.