Extending Tactical Asset Allocation Backtests with Synthetic Histories

Summary

This article explains why tactical asset allocation strategies can be difficult to evaluate over long periods: allocation signals are often monthly, leaving relatively few observations, and market regimes may persist for years. Retail investors may also lack affordable access to long histories across asset classes. The proposed workaround is to extend an ETF’s record with earlier returns from a related market index, subtracting a proxy for the ETF’s expenses. For example, index returns can stand in for an ETF before the fund began trading.

The article stresses that the extension is an approximation, not a substitute for traded ETF data. Historical index series may provide closing prices only, while a live strategy may require open prices to model next-session orders. Forward-filling a prior close as an open is unrealistic; trading at the close instead requires assumptions about market-on-close execution. The method can offer an indicative view across more market regimes, but price timing, costs, and implementation assumptions limit how faithfully it represents achievable results. Corporate actions and rebalance timing are flagged as further issues.

Key ideas

• Monthly allocation strategies often have few observations and need long histories to span different market regimes.
• Pre-inception ETF returns can be approximated with related index returns adjusted for estimated fund costs.
• Index histories may lack open prices needed to model next-session rebalancing.
• Forward-filling prior closes or simulating close-time trading introduces execution assumptions.
• Synthetic extensions are useful as indicative evidence but do not reproduce actual ETF trading history.

Tags

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