Market-Neutral Stock Trades with Eigenportfolios

Summary

The document explains how a statistical arbitrage trade using principal-component eigenportfolios can pair an individual stock position with positions in portfolios representing common movements across stocks. In the paper’s sector or industry approach, the example is long a stock and short an appropriate amount of sector or industry exchange-traded funds. The PCA approach is described as regressing a stock on eigenportfolios and offsetting its estimated exposures by shorting those portfolios when going long the stock.

This construction aims to separate a stock’s relative movement from broader systematic components. The source points to the paper’s discussion of entry and its PCA backtests, but notes that those sections offer limited detail. The interpretation of the backtest method is tentative, and the document supplies no performance evidence, sizing rules, or implementation guidance. It is therefore a concise explanation of the trade’s hedge structure rather than a full strategy specification.

Key ideas

• An eigenportfolio trade can pair a long stock position with short positions in portfolios of common stock movements.
• A sector-based variant offsets a stock position with suitable sector or industry exchange-traded funds.
• A PCA approach can estimate a stock’s exposure to eigenportfolios through regression and hedge those exposures.
• The described paper gives limited detail on its PCA backtest implementation, so the interpretation is provisional.

Tags

# Statistical arbitrage using eigen portfolios


# Statistical arbitrage using eigen portfolios












I was trying to understand below paper

https://www.math.nyu.edu/faculty/avellane/AvellanedaLeeStatArb071108.pdf

Page 20 explains about "Entering a trade". I wan't to know clearly what it means to place a long trade in case of arbitrage using eigen portfolios.

Greatly appreciate your inputs

## Answer by John (score 2)

https://quant.stackexchange.com/a/15149

The paper alternatives between using eigenportfolios and sector/industry ETFs for statistical arbitrage. For instance, sections 2.1-2 vs. 2.3.

The trade in Section 4.1 is long some stock and short an appropriate amount of sector/industry ETFs.

That being said Sections 5.3 and 5.4 discuss PCA strategies in a backtest, with relatively little additional information. It seems they are using the approach described at the beginning of Section 5 (basically they regress the stock against 15 or so eigenportfolios and go long the stock and short the eigenportfolios based on the beta, assuming I'm reading it correctly).

Shown in full with attribution under the source's licence. Licence: CC BY-SA 4.0 (Stack Exchange)

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