Z-Score Mean Reversion for Gold-Silver Pair Trading

Summary

This statistical arbitrage method trades a normalized relationship between silver and gold. It scales each price against its 20-period simple moving average, forms a ratio, smooths it with a short exponential average, and calculates a rolling Z-score. A move below the negative threshold signals a long, while a move above the positive threshold signals a short; a 14-period RSI filter gates the entries.

The described exits use volatility-based levels: a profit target at three ATR and a stop at eight ATR, with ATR measured over 14 periods. The text claims historical backtests show positive expected returns, but supplies no performance statistics or detailed evidence. It favors range-bound conditions and warns that persistent trends or structural changes in the gold-silver relationship can cause losses. The supplied settings identify a futures venue, but do not establish robustness across markets, costs, or time periods.

Key ideas

• The strategy estimates relative deviation using a normalized silver-to-gold ratio and a rolling Z-score.
• It enters mean-reversion trades at extreme Z-score readings, subject to an RSI filter around its midpoint.
• ATR-based exits set a closer profit target and a wider stop, according to the stated multiples.
• The approach is intended for ranging markets and may suffer when the relationship shifts or trends persist.
• The document asserts favorable backtest behavior but gives no quantitative results to evaluate that claim.

Tags

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