Skip to main content
Track Trend filter
5 / 33
Library

1992issue C101-9

Phase diagrams for moving-average trend filters

An indicator-phase-diagram treats every moving-average length as a signed trend state on one chart. Short filters lead longer ones through zero, and a crossing is accepted as a usable trend-filter flip only when it lands inside a wide, historically coherent band of neighboring lengths.

  • Phase is the signed distance of the close from a moving average: positive when price is above that average and negative when price is below it.
  • An indicator-phase-diagram plots lookback length against that signed gap so one snapshot shows which lengths sit above or below the filter.
  • Transitions travel from shorter lookbacks toward longer ones because longer moving averages lag more and reverse later.
  • A single phase-transition was not treated as sufficient; a crossing was taken as meaningful only inside a scoring-plateau, not on an isolated optimization-cliff.
Entries in this reading2 entries

What phase measures

For a simple moving average, phase is the signed distance of the close from that average. The reading is positive when price is above the average and negative when price is below it.

A phase-transition is defined as the indicator crossing the center of its range. For this trend-filter, that is the moment price crosses the chosen lookback.

How the diagram is drawn

An indicator-phase-diagram places lookback length on the horizontal axis and the signed price-to-average gap on the vertical axis. One snapshot then shows which lengths are currently above or below the filter.

Logarithmic horizontal scaling was used so a single diagram can compress lookbacks from very short to very long sampling intervals.

A single index snapshot

In the 1991-12-02 index snapshot, the close sat above lookbacks 5 through 12 and below lookbacks 14 through 70, locating the zero crossing at the 13-day average.

Why short lengths lead

Viewed as a sequence, transitions travel from shorter lookbacks toward longer ones because longer moving averages lag more and reverse later. That delayed march is the lookback-wave: the same crossing arriving later at longer sampling intervals.

When a crossing counts

Any single crossing was not treated as sufficient. Significance required the lookback to sit inside a broad, stable historical scoring band rather than a narrow isolated island.

On the index scoring map, isolated lookbacks below 43 were treated as unstable optimization-cliff islands. The contiguous 48-to-65 band was treated as the scoring-plateau, the region where a crossing would be taken as meaningful.

A listed-stock decision

In the listed-stock case, a 13-day crossing was rejected because it sat in a historically poor-scoring region. A later 38-day crossing inside a broad scoring-plateau was accepted as the state change.

Other ways to measure phase

Phase can be built as a raw price-minus-indicator gap, a percentage of the indicator, a standardized distance around an envelope, or, for bounded oscillators, a distance from the midpoint of the oscillator range.

Educational research material, not investment advice. Historical source context does not establish present-day performance.
5 of 33 in the Trend filter track
19931-10 pp.Next on Trend filterVolume-weighted change smoothing and trend rankingMarket-volume-impact is the product of a session net price change and the volume recorded with that change, not a change scored against calendar time.
All readings on this track · 33 readings
  1. 1988Opening-range brackets, a two-bar trend filter, and bounded stops
  2. 1990Bezier-curve price trend filter
  3. 1992Constructing a damping-index trend filter
  4. 1992Building a random walk index trend filter
  5. 1992Phase diagrams for moving-average trend filters
  6. 1993Volume-weighted change smoothing and trend ranking
  7. 1993Concurrent highest-low filter with a largest-low-fall trigger
  8. 1994Unit-invariant trend filters and the c-test
  9. 1995Constructing cup and cap entries with a three-bar net line
  10. 1997Why a daily timing evaluation depends on interval, lookbacks, and the fitting objective
  11. 2001A volume budget clock for trend-segment construction
  12. 2001Keep three jobs separate when you test a composite score
  13. 2002Evaluating the weekly four-percent close filter as a market-state procedure
  14. 2003Constructing a confirmed zigzag trend filter
  15. 2004Decompose high, low, and close into separate forecast streams
  16. 2005Three-state moving-average breakout bar coloring
  17. 2005Constructing a volume and move-adjusted trend filter
  18. 2005A fifty-day average breakout as a trend permission filter
  19. 2005Current-bar inclusion can mute a stochastic channel break
  20. 2006A stochastic oscillator gated by a long-term exponential average
  21. 2010A construction test for a modified volume-price trend filter
  22. 2011Constructing a Spearman rank trend filter
  23. 2013Constructing a repeated-median slope as a resistant trend filter
  24. 2014Combining a relative-strength index and trend filters for oversold setups
  25. 2014Price-rooted lookbacks for a relative strength index, a moving average, and a trend filter
  26. 2015Evaluating next-session intermarket range forecasts
  27. 2018Read the intermarket weight matrix first, then the predicted moving-average filter
  28. 2018Constructing the stiffness trend filter from moving-average holds
  29. 2018The averaging kernel and the lagged trend gate are separate specifications
  30. 2019A trend filter is not ready to compare until portfolio constraints are written down
  31. 2019Lookback, threshold, and position-capacity for a stiffness trend-filter
  32. 2020Combining a trend filter with a moving average and a stochastic oscillator
  33. 2020Constructing a relative-strength oscillator with a rank-agreement trend filter
All 137 readings tagged Trend filter
Also on Trend filter5 readings