Skip to main content
Track Fourier analysis
22 / 26
Search the archiveLibrary
Library

2010issue C0442-49

Why cycle indicators fail when parameters shift

A deterministic signal-processing model of price is a teaching simplification used to split a series into a constant, a trend, cyclical components, and noise. Fourier analysis and Spectral analysis can estimate cycle content in ordered prices, but those estimates remain historically contingent when the filter settings change.

  • A deterministic signal-processing model of price is a teaching simplification, not a claim that markets are accurately described as non-random.
  • Price can be decomposed into a constant, a trend, cyclical components, and noise so that an indicator is judged by which term it tries to isolate.
  • Fourier analysis and Spectral analysis can estimate cycle content in ordered price series, but those estimates are historically contingent rather than guaranteed forecasts.
  • Editorial view: treat Dominant cycle detection and related cycle indicators as parameter-sensitive filters, not as proof that markets contain a stable, tradable rhythm.
Entries in this reading3 entries
Current trackFourier analysis41 readingsSpectral analysis63 readingsDominant cycle detection180 readings

A teaching simplification

A deterministic signal-processing model of price is a teaching simplification. It is not a claim that markets are accurately described as non-random.

The historical workflow decomposes price into a constant, a trend, cyclical components, and noise. Once those terms are named, an indicator can be judged by which term it tries to isolate.

S&P 500 daily prices used to introduce the signal model

The path already shows a floor well above zero, a net rise, several multi-week swings, and short-term noise — the four terms in the article's teaching model. Approximate closes were read from the published Figure 1 bar chart against its printed Price 1100–1300 and Day 1–201 scales.
The path already shows a floor well above zero, a net rise, several multi-week swings, and short-term noise — the four terms in the article's teaching model. Approximate closes were read from the published Figure 1 bar chart against its printed Price 1100–1300 and Day 1–201 scales.S&P 500 · 201 daily bars

The source figure is an OHLC bar chart; only approximate closes are recovered. Vertical labels 1100, 1150, 1200, 1250, 1300 and horizontal labels 1, 51, 101, 151, 201 come from the article. Values are rounded to five index points because the raster cannot support finer precision.

What the estimates can show

Fourier analysis and Spectral analysis can estimate cycle content in an ordered price series. Dominant cycle detection then names a prevailing cyclical component from that estimate.

The archive treats those estimates as historically contingent rather than as guaranteed forecasts. They describe ordered observations under a chosen decomposition. They do not, by themselves, show that a durable rhythm has been found.

Keep the forecast in context

A readout from Dominant cycle detection, Fourier analysis, or Spectral analysis should be read as a historically contingent description of past ordered observations. It is not a guaranteed forecast.

That reading keeps the deterministic model in its proper place: a teaching aid for judging which term a tool tries to isolate, not a claim that price is accurately non-random.

Educational research material, not investment advice. Historical source context does not establish present-day performance.
22 of 26 in the Fourier analysis track
201916-19 pp.Next on Fourier analysisConstructing futures momentum as open-interest-scaled rate of changeMinute-to-day discovery prints are treated as noise that samples nearby bid and ask intensity, while the longer-horizon object is the multi-week to multi-month price oscillation.
All readings on this track · 26 readings
  1. 1982Critiquing Fourier, Elliott, and seasonal commodity models
  2. 1982Evaluating half-hour crossovers with cycle priors and stops
  3. 1984Building moving-window spectral cycle forecasts
  4. 1988Fourier cycles versus calendar seasonal regimes
  5. 1989Constructing analog cycle signatures from price lows
  6. 1990Curve fits fail the forecast test
  7. 1991Auditing moving-average length with Fourier spectra
  8. 1991Closed-form phase for dominant-cycle spectra
  9. 1993Evaluating windowed spectral forecasts of index turning points
  10. 1994Window length for moving-window spectral forecasts
  11. 1994Constructing WAMI power and phase spectra
  12. 1994Fourier-tuned momentum filter design
  13. 1994Aliasing, leakage, and dominant-cycle reads from sampled prices
  14. 1995Constructing indicator lookbacks from Fourier spectra
  15. 1996Constructing phase from a dominant-cycle sine and cosine pair
  16. 1999Sinusoidal pseudo-securities for indicator evaluation
  17. 2000Constructing dominant cycle length from Hilbert phase
  18. 2000Constructing adaptive channel breakouts from a measured cycle period
  19. 2005Embedding forex prices into a singular-spectrum forecast basis
  20. 2005Constructing recurrent forecasts from grouped spectral components
  21. 2007Constructing a dominant cycle from transformed Fourier spectra
  22. 2010Why cycle indicators fail when parameters shift
  23. 2019Constructing futures momentum as open-interest-scaled rate of change
  24. 2019Judging a dominant cycle and a trend filter by sample, lag and the move they keep
  25. 2020Constructing futures turnover time and urgency
  26. 2020Stock power ratio as a growth trend filter
By fieldCycles and spectral analysis129 readingsBy year2010169 readings
All 41 readings tagged Fourier analysis
Also on Fourier analysis5 readings
1984Building moving-window spectral cycle forecasts1989Constructing analog cycle signatures from price lows1991Auditing moving-average length with Fourier spectra1991Closed-form phase for dominant-cycle spectra1993Evaluating windowed spectral forecasts of index turning points