Skip to main content
Track Maximum entropy spectrum analysis
9 / 28
Search the archiveLibrary
Library

1989issue C051-5

Evaluating next-session cycle forecasts with stops

A spectral next-session call can be scored twice: first on whether the projected slope matches the cash close-to-close move, then on whether the same call, after a low-content skip and an opening stop, still describes the futures open-to-close path.

  • Next-session direction came from the slope of a short projected path, not from a half-cycle hold at a peak or trough.
  • Cash close-to-close direction and futures open-to-close results were scored as separate tests because a correct index call did not always match the futures session.
  • Low spectrum content and poor-resolution warnings withheld a directional call, and a stop-loss booked an opening-to-adverse-extreme limit instead of the close.
  • Adding costs and the stop changed counted wins when a small correct session move failed to cover costs or an early stop differed from holding to the close.
Entries in this reading3 entries
Current trackMaximum entropy spectrum analysis30 readingsDominant cycle detection119 readingsStop-loss order144 readings

Two tests for one spectral call

The evaluated design read next-session direction from a maximum-entropy spectrum of the latest observations and a short projected continuation of that path. The recovered cycle, or set of cycles, was treated as the dominant cycle for the next interval, so the slope of the projected path could be read as a long or short mark for the following session only.

Editorial reading: treat that mark as two tests, not one. First ask whether the projected slope matches the cash close-to-close move. Then ask whether the same call, after a low-content skip and an opening stop, still describes the futures open-to-close path.

How the next-session mark was formed

A maximum-entropy spectrum is a short-lookback spectrum of ordered observations used to recover cycles in a window and project a brief continuation path. After a synthetic check, the slope of that projected curve was treated as the next-session long or short signal rather than as a half-cycle hold from a peak or trough.

The working sample was a rolling lookback updated each evening. The next session was marked long, short, or later as no-trade. Next-session direction meant entry at the open and exit at the close unless a skip or stop intervened.

A synthetic check before market data

Before market data were used, the same spectrum was checked on a compound synthetic series built from out-of-phase sine waves with drifting periods and amplitudes. Only after that check was the slope of the projected path read as next-session direction.

Cash close-to-close versus futures open-to-close

Close-to-close cash-index direction was scored separately from open-to-close futures results. A correct index call did not always match the futures session. That mismatch is index-futures slippage: a correct cash close-to-close call fails to stay in synch with the futures open-to-close move because of premium shifts or opening gaps.

A skip filter and an opening stop

Low spectrum content and poor-resolution warnings were used as a cycle-content filter. Those days were not given a next-session direction.

A stop-loss column compared the opening-to-adverse extreme with a limit. On a hit, that limit was booked as the day's result instead of the close. The stop-loss here is a pre-set opening-to-adverse-extreme limit that ends a same-session position at a fixed loss instead of holding to the close.

Why counted wins changed

Adding costs and the stop changed counted wins. A small correct session move might fail to cover costs, and an early stop could differ from holding to the close. Editorial reading: the cash-direction test and the futures path after skip, stop, and costs answer different questions about the same spectral call.

Next-session MESA slope hits after the content skip

Once low-content and poor-resolution days are dropped, the same next-session slope still matches 87% of cash S&P 500 close-to-close moves, but only 62% of front-month futures open-to-close paths, and a 150-point opening stop plus $45 commissions leaves 51% winners. The second test fails in the 19 Aug–15 Sep window (10% futures-path hits). Percentages are read from the article’s filtered trading-results table (55 trades), not traced from a plot.
Once low-content and poor-resolution days are dropped, the same next-session slope still matches 87% of cash S&P 500 close-to-close moves, but only 62% of front-month futures open-to-close paths, and a 150-point opening stop plus $45 commissions leaves 51% winners. The second test fails in the 19 Aug–15 Sep window (10% futures-path hits). Percentages are read from the article’s filtered trading-results table (55 trades), not traced from a plot.S&P 500 cash index and nearest-term S&P 500 futures · next session, daily · 1988-06-01T00:00:00.000Z to 1988-09-15T00:00:00.000Z

MESA was run on the last 60 S&P 500 cash closes. Sessions flagged for low spectral content or poor resolution were skipped. The stop column uses a 150-point limit from the futures open and a $45 commission.

Educational research material, not investment advice. Historical source context does not establish present-day performance.
9 of 28 in the Maximum entropy spectrum analysis track
19891-5 pp.Next on Maximum entropy spectrum analysisConstructing cycle-aged volatility trailing stopsA generalized trailing stop has two parts: an initial offset large enough for ordinary price noise, and a later tightening schedule that reduces remaining room after a significant reversal.
All readings on this track · 28 readings
  1. 1984Constructing maximum-entropy spectra for dominant-cycle forecasts
  2. 1984How to construct a maximum-entropy cycle model
  3. 1984Constructing a maximum-entropy forecast from a chosen lookback
  4. 1985Constructing period-locked half-cycle and full-cycle averages
  5. 1986Why Fourier windows limit dominant-cycle resolution
  6. 1987Assembling short-lookback maximum-entropy cycle forecasts
  7. 1988Why a fitted dominant cycle is not a forecast
  8. 1989Evaluating commodity cycle personalities with spectral histograms
  9. 1989Evaluating next-session cycle forecasts with stops
  10. 1989Constructing cycle-aged volatility trailing stops
  11. 1990A channel signal-to-noise gate for dominant-cycle forecasts
  12. 1990Year-over-year dominant cycle personality audit
  13. 1991Cyclic entry from a locked dominant-cycle phase
  14. 1992Stationarity states on synchronized futures spectral contours
  15. 1997Hidden horizon assumptions in dominant-cycle readings
  16. 1997When market cycles are absent more than present
  17. 1997A spectral estimator that retunes indicators to the measured cycle
  18. 2000Constructing a Hilbert dominant cycle and a maximum-entropy refinement
  19. 2000Switch trend and cycle indicators after a half-cycle dwell test
  20. 2000Constructing a dominant-cycle squelch trend filter
  21. 2000Phasor displays for dominant-cycle construction
  22. 2002Low-lag trendline from elliptic and dominant-cycle notches
  23. 2004Spectral peaks are mode diagnostics, not forecasts
  24. 2004Compressive last-stage oscillator construction
  25. 2013Constructing trend failure curves from qualified-trend transitions
  26. 2014Lookback range, a two-lag smoother, and next-bar fills
  27. 2014Constructing a MESA stochastic with roofing and SuperSmoother filters
  28. 2016Constructing spectral heatmaps for dominant market cycles
By fieldCycles and spectral analysis77 readingsBy year198983 readings
All 30 readings tagged Maximum entropy spectrum analysis
Also on Maximum entropy spectrum analysis5 readings
1984How to construct a maximum-entropy cycle model1984Constructing maximum-entropy spectra for dominant-cycle forecasts1985Constructing period-locked half-cycle and full-cycle averages1986Why Fourier windows limit dominant-cycle resolution1987Assembling short-lookback maximum-entropy cycle forecasts