Illustrative mathematical surface · Research note
Looking past average returns to examine the behavior, exposure, and fragility of a simple equity factor. This illustrative research note sets out an approach, its assumptions, and the questions left open.
Research
repositories
Get the notebooks, modeling code, and supporting datasets behind the videos as they become available.
- Full research archive
- New published projects
- Reproducible experiments
Membership opens when the first repository files are ready. No payments are being collected.
Recurring monthly subscription · Cancel anytimeA factor is more than its mean
Sorting stocks by a characteristic can produce an attractive average spread. The path, concentration, and changing exposures behind that average deserve equal attention.
Methodology
Define the investable universe before choosing the factor. Use point-in-time data and include delisted securities where the dataset permits. Rebalance on a fixed schedule and document treatment of missing observations.
A simple regression can help describe market exposure. It cannot prove a causal source of returns.
Reproducible checks
# Research outline; inputs must be point-in-time.
rank = characteristics.rank(pct=True)
long = rank > 0.8
short = rank < 0.2
Track turnover, sector composition, and weight concentration. Compare equal-weighted and capitalization-weighted portfolios. Preserve a final holdout period for one-time evaluation.
Findings to investigate
Ask whether an apparent premium is concentrated in small, illiquid securities or in a narrow historical window. Test whether the proposed explanation predicts where the factor should become weaker.
Limitations
No empirical factor premium is claimed. Data availability, borrow costs, corporate actions, and execution assumptions can substantially alter an eventual result.
