Skip to main content
Track Robustness testing
29 / 51
Search the archiveLibrary
Library

2002issue C061-4

Evaluating two-window trend intensity as a reversal rule

A 30-period trend intensity index scores recent up-deviation mass against a 60-period average of closes. The historical workflow made that reading testable by locking next-open reversal rules, one shared lookback, and the same 80/20 thresholds, then repeating the procedure in a lookback sweep.

  • The trend intensity index is a 0 to 100 share of recent up-deviation mass among all close-to-average deviations over the shorter window.
  • The mechanical procedure became a reversal engine only after a reading above 80 or below 20 set a long or short stance at the next open and that stance was held until the opposite threshold was crossed.
  • The same lookback and the same 80/20 thresholds were applied to fifteen continuous-contract futures series, so the intensity window was not chosen market by market.
  • Robustness testing held the entry, hold, reverse, and portfolio rules fixed and repeated the procedure at intensity windows of 20, 25, 30, 35, and 40 periods.
Entries in this reading3 entries
Current trackRobustness testing58 readingsTrend filter137 readingsMechanical trading system158 readings

What the two-window reading measures

The trend intensity index is built from a two-window construction. A 60-period simple average of closes sets the reference level. Each of the last 30 closes is then compared with that average. Residuals above the average are up-deviations. Residuals below it are down-deviations. The index is the up-deviation sum divided by the combined up and down sums, then scaled by 100.

The index is bounded between 0 and 100. A reading above the intensity midpoint of 50 means recent up-deviation mass exceeds down-deviation mass. A reading below 50 means the opposite. Trend intensity is the distance from that midpoint toward 100 or toward 0.

Why the two windows are paired

The construction rationale is that, in a persistent rise spanning the longer average window, most closes in the recent half of that window should sit above the average, so the up-share of deviations should exceed one half. The opposite pattern is expected in a persistent decline.

How the reversal procedure is locked

The mechanical procedure treated the index as a reversal engine. It went long the next open after a reading above 80, went short the next open after a reading below 20, and kept the existing stance until the opposite threshold was crossed. Next-open execution takes the stance implied by today’s completed reading at the following session’s open.

How a spreadsheet implements the same rules

A spreadsheet implementation first forms the 60-period average, then the 30-period sum of absolute close-to-average deviations, the signed 30-period residual sum, the implied up-deviation sum, and the percentage index. The position cell becomes 1, -1, or the prior stance according to the 80/20 thresholds. A new fill is taken at the next open only when that stance changes.

Yen 30-day TII, late December 1998

On the continuous yen contract the 30-day trend intensity index falls from 77.23 on 17 December 1998 through the 50 midline to 47.95 by year-end, so the next-open reversal rule stays flat (column K = 0) because the reading never clears 80 or 20. Numbers are the J-column TII values in the article’s Excel sidebar, not a redraw of the sheet.
On the continuous yen contract the 30-day trend intensity index falls from 77.23 on 17 December 1998 through the 50 midline to 47.95 by year-end, so the next-open reversal rule stays flat (column K = 0) because the reading never clears 80 or 20. Numbers are the J-column TII values in the article’s Excel sidebar, not a redraw of the sheet.Yen (continuous futures) · daily · 1998-12-17T00:00:00.000Z to 1998-12-31T00:00:00.000Z

Sidebar uses continuous-contract yen from 23 September through 31 December 1998; TII is defined only from the first complete 60-day average (row 61). Same 80/20 next-open lock as the 15-market test.

What stayed fixed across the sample

The historical procedure applied the same lookback and the same 80/20 thresholds to fifteen futures series. It used a continuous-contract sample, allowed one contract per entry, deducted 75 currency units per trade for costs, and ran from 4 January 1982 through 31 December 1998. Any stance still open on the final sample date was closed at that session’s close rather than left unmarked.

How the lookback sweep tests robustness

Robustness was examined by holding the entry, hold, reverse, and portfolio rules fixed and repeating the test at intensity windows of 20, 25, 30, 35, and 40 periods instead of choosing a separate length for each market. The lookback sweep therefore changes only the shorter intensity window while the reversal procedure stays the same.

Educational research material, not investment advice. Historical source context does not establish present-day performance.
29 of 51 in the Robustness testing track
20031-4 pp.Next on Robustness testingDiscounting speculative bubbles in system robustness testsExtraordinary speculative episodes can dominate a historical record, so a short recent sample is a weak basis for judging long-term viability.
All readings on this track · 51 readings
  1. 1986Degrees of freedom in trading system optimization
  2. 1988Walk-forward and neighborhood tests after optimization
  3. 1988Undisclosed rules block system robustness tests
  4. 1988Testing re-optimization calendars against random parameter controls
  5. 1989Binary search limits on multi-peak average grids
  6. 1989Parameter neighborhoods that survive a shift
  7. 1990Use profit mapping to keep a cycle and stop plateau
  8. 1990Why popular indicator optimization fails robustness
  9. 1991Retesting weighted indicator balances across horizons
  10. 1992Constructing forecast models with regression, walk-forward, and robustness
  11. 1992Diagnose regimes before you lock parameters
  12. 1992When stops change system timing
  13. 1993Walk-forward halt rules for forecast models
  14. 1994Walk-forward evaluation of genetic index rules
  15. 1995Input pruning as walk-forward system evaluation
  16. 1995Critiquing neural nets as incomplete trading systems
  17. 1996Rebuild the equity-path ratio before it ranks a designed system
  18. 1996Parameter grids can fit random walks
  19. 1996Walk-forward analysis belongs in the design of a mechanical trading system
  20. 1997When a holdout fails, discard the rule set
  21. 1997Test rewarded rule breaks before replacing the system
  22. 1997Walk-forward rules keep system research from rewriting live trades
  23. 1999Keep a channel-breakout to two lookbacks and test neighbor stability
  24. 1999Constant investment size in stock system evaluation
  25. 2000Forcing optimization maps mechanical system failure boundaries
  26. 2000Robust parameter selection with surface charts
  27. 2001A two-gate classroom test for a two-window momentum trend filter
  28. 2002How a two-sided continuation factor becomes a testable trend rule
  29. 2002Evaluating two-window trend intensity as a reversal rule
  30. 2003Discounting speculative bubbles in system robustness tests
  31. 2003Walk-forward evaluation of locked stochastic oscillator rules
  32. 2003Critiquing mechanical system design after extreme price regimes
  33. 2004Evaluating a two-window trend trigger
  34. 2005Grade backtested signals with holdouts and optimization plateaus
  35. 2006Reserved-sample evaluation of trading system design
  36. 2006Walk-forward critique of hindsight crossover systems
  37. 2008Condition-matched walk-forward evaluation for mechanical systems
  38. 2011Session-split evaluation of regular and overnight systems
  39. 2012Walk-forward evaluation as operator rehearsal
  40. 2013Two-window evaluation of mechanical trading systems
  41. 2013Walk-forward filter selection for repeated-median velocity
  42. 2014Walk-forward evaluation for fading-memory velocity systems
  43. 2015Test oscillator events before tuning rules
  44. 2016Walk-forward evaluation of a five-parameter parabolic stop-and-reversal
  45. 2016Walk-forward optimization without curve fitting
  46. 2017Optimization without overfitting in trend-system evaluation
  47. 2017Parameter stability is a better guide than a larger crossover grid
  48. 2018Point-in-time universes for system evaluation
  49. 2018Walk-forward robustness evaluation for optimized systems
  50. 2018Critiquing breakout systems through robustness tests
  51. 2018A critique of parameter fitting in system design
By fieldIndicators and filters682 readingsBy year200284 readings
All 58 readings tagged Robustness testing
Also on Robustness testing5 readings
2004Evaluating a two-window trend trigger2001A two-gate classroom test for a two-window momentum trend filter2013Walk-forward filter selection for repeated-median velocity1988Isolate nested formulas before judging signals1988Undisclosed rules block system robustness tests