2002issue C121-3
Evaluating the weekly four-percent close filter as a market-state procedure
Once the percent threshold, the weekly sampling interval, the stance mode, and the fixed-share-unit are frozen, a weekly-percent-change-switch is a complete, testable trend-filter. Editorial: read that stance as a market-state overlay that can sit beside a moving-average baseline, not as a finished profit engine.
- A weekly-percent-change-switch becomes a testable mechanical-trading-system only after the percent threshold, the weekly sampling interval, the stance mode, and the fixed-share-unit are frozen.
- The same weekly close rule can run in long-only-mode, which moves to cash on a sell, or in long-and-short-mode, which reverses on each opposite signal.
- An annual-reset starts each calendar year at the first new buy or sell signal and omits prior-year balances, except for a separate three-year cumulative series.
- Editorial: treat the filter as a market-state read across the Nasdaq 100, the S&P 500, and the Dow industrials, and keep a moving-average as a companion baseline rather than as the primary switch.
What the weekly switch classifies
The subject rule is presented as an always-in-the-market trend-filter applied to weekly closes. It is a weekly-percent-change-switch: a long signal fires when the latest weekly close is at least four percent above the prior weekly close, and a sell or reverse signal fires when the latest weekly close is at least four percent below.
A trend-filter classifies ordered price observations into an up or down regime over a stated sampling interval and lookback. Here the sampling interval is the weekly close, and the lookback is the prior weekly close.
Freeze the free choices
Editorial: the switch is not yet a complete mechanical-trading-system until every free choice is frozen. Freeze the four percent threshold, the weekly sampling interval, long-only-mode or long-and-short-mode, and a fixed-share-unit that trades the same share count on every signal.
A mechanical-trading-system is a fully specified procedure that turns rule inputs, market state, and execution constraints into entry, exit, or abstention signals. After those items are fixed, the resulting stance can be tested as one procedure.
Two ways to handle a sell
The same mechanical-trading-system can be run in long-only-mode by moving to cash on a sell, or in long-and-short-mode by reversing on each opposite weekly signal. Long-only-mode exits to cash instead of opening a short position. Long-and-short-mode stays in the market by reversing from long to short, or short to long, at each opposite signal.
Study cuts and listed vehicles
The post-2000 Nasdaq 100 test used a fixed 100-share unit and required 20000 in cash or cash-plus-margin purchasing power at the 2000 start. That fixed-share-unit does not resize with price or equity.
Each annual study uses an annual-reset. It starts at that year’s first buy or sell signal and omits prior-year balances, except for a separate three-year cumulative series.
The 1985 to 2000 extension applied the same filter to the S&P 500, the Dow Jones Industrial Average, and the Nasdaq, rather than to the earlier Value Line composite window. After 2000 the filter is concentrated on the Nasdaq 100 tracker because that index offered listed vehicles including the fund, options on the fund, and e-mini futures.
The 2002 Nasdaq 100 path is reported only through 30 August. That year is described as having produced slightly more than half as many trades as each of the prior two years.
A market-state overlay beside a moving-average
The archive write-up treats the filter more as a market-state read across the Nasdaq 100, the S&P 500, and the Dow industrials, to be combined with companion models such as moving averages, than as a self-contained mechanical strategy.
A moving-average is a smoothing of ordered price observations over a defined lookback, used here as a companion baseline rather than as the primary switch. Editorial: keep the moving-average in that companion role and keep the weekly filter as a market-state overlay.
All readings on this track · 33 readings
- 1988Opening-range brackets, a two-bar trend filter, and bounded stops
- 1990Bezier-curve price trend filter
- 1992Constructing a damping-index trend filter
- 1992Building a random walk index trend filter
- 1992Phase diagrams for moving-average trend filters
- 1993Volume-weighted change smoothing and trend ranking
- 1993Concurrent highest-low filter with a largest-low-fall trigger
- 1994Unit-invariant trend filters and the c-test
- 1995Constructing cup and cap entries with a three-bar net line
- 1997Why a daily timing evaluation depends on interval, lookbacks, and the fitting objective
- 2001A volume budget clock for trend-segment construction
- 2001Keep three jobs separate when you test a composite score
- 2002Evaluating the weekly four-percent close filter as a market-state procedure
- 2003Constructing a confirmed zigzag trend filter
- 2004Decompose high, low, and close into separate forecast streams
- 2005Three-state moving-average breakout bar coloring
- 2005Constructing a volume and move-adjusted trend filter
- 2005A fifty-day average breakout as a trend permission filter
- 2005Current-bar inclusion can mute a stochastic channel break
- 2006A stochastic oscillator gated by a long-term exponential average
- 2010A construction test for a modified volume-price trend filter
- 2011Constructing a Spearman rank trend filter
- 2013Constructing a repeated-median slope as a resistant trend filter
- 2014Combining a relative-strength index and trend filters for oversold setups
- 2014Price-rooted lookbacks for a relative strength index, a moving average, and a trend filter
- 2015Evaluating next-session intermarket range forecasts
- 2018Read the intermarket weight matrix first, then the predicted moving-average filter
- 2018Constructing the stiffness trend filter from moving-average holds
- 2018The averaging kernel and the lagged trend gate are separate specifications
- 2019A trend filter is not ready to compare until portfolio constraints are written down
- 2019Lookback, threshold, and position-capacity for a stiffness trend-filter
- 2020Combining a trend filter with a moving average and a stochastic oscillator
- 2020Constructing a relative-strength oscillator with a rank-agreement trend filter