Using Likelihood Models to Rotate Between Large-Cap and Small-Cap Sectors

Summary

The document summarizes research on long-horizon rotation between large-cap, high-ROE sectors and smaller-cap sectors. It argues that their relative performance can shift over periods of years, and that size-based and ROE-based rotations may move together. Changes in high- versus low-ROE leadership may precede size rotations, although the lead time is uncertain.

The proposed method estimates which normal-return regime is most likely using a maximum-likelihood comparison of normal distributions, then uses the inferred long-term direction to choose between sector groups. The central argument is that persistent trends can arise from sequences with different means even without return autocorrelation or a predictive signal for the next period. The summary reports historical annualized results since 2009 against the CSI 300, but supplies no underlying data, detailed implementation, risk measures, or validation beyond that reported period, so the figures do not establish future performance.

Key ideas

• Large-cap and small-cap sectors can alternate in relative performance over multi-year periods.
• Size leadership and high- versus low-ROE sector leadership may rotate in related ways.
• The described strategy uses maximum likelihood to classify returns by their likely mean regime.
• Long-term direction can persist without serial correlation or accurate next-period forecasts.
• The reported historical comparison lacks implementation and risk details in the available summary.

Tags

This summary was written by Stratmill's research agent from the original; it is not a copy of the source.