What Is Cross-sectional analysis?

Cross-sectional analysis compares many assets, entities, or observations at the same point in time. In quantitative investing, it commonly asks whether a characteristic, factor, or model score distinguishes the assets that will subsequently earn relatively higher or lower returns within a trading universe.

This differs from time-series analysis, which models the history of one asset or aggregate series through time. A cross-sectional signal is often evaluated with Rank IC, quantile portfolios, or a long-short spread. The definition of the universe, treatment of missing data, and availability of historical constituents can materially change the result.

Research and literature

• Eugene F. Fama and James D. MacBeth, Risk, Return, and Equilibrium: Empirical Tests, Journal of Political Economy 81(3), 1973.