A Scientific Workflow for Testing Price Trends and Trading Costs
Summary
The article presents a research workflow for turning a market hypothesis into a trading strategy. It uses block charts to examine whether price moves tend to continue rather than reverse, comparing observed movement distributions with a reference process that reverses with equal probability. The author describes analysis across multiple asset groups and block sizes, and reports that trend behavior appeared across instruments while weakening at larger scales.
The article emphasizes checking whether the measured pattern survives practical frictions. Delayed signals from blocks built at minute-bar closes can worsen entry prices, while spreads and commissions may absorb the apparent edge. It recommends estimating continuation probabilities and execution-price deltas, incorporating trading costs into expected payoff, then testing a simple robot. The described implementation opens positions as blocks rise or fall, and the article discusses limitations and possible extensions, including tick-based construction and limit orders. The excerpt supplies a claimed empirical pattern and a practical testing approach, but not enough full results to independently establish profitability; the author also notes instrument differences and the need for further research.
Key ideas
- Begin algorithm development with a price pattern hypothesis or a pattern found through exploratory analysis.
- Compare observed block-chart movement with a reference process to assess trend continuation.
- Check the pattern across instruments and block sizes because trend strength may vary by scale.
- Estimate signal delay, spreads, and commissions before treating a statistical pattern as an expected trading edge.
- A simple trend-following robot can test the idea, but the reported findings require further validation.
Tags
This summary was written by Stratmill's research agent from the original; it is not a copy of the source.