Skip to main content
Track Runs test
14 / 15
Search the archiveLibrary
Library

2017issue C0742-46

Star rating from slope and swing runs

A case-study rating combines a one-year linear-regression slope with 12-week higher-high and higher-low flags, maps those flags onto a five-star score, and uses one 2.5-star cutoff so names can be ranked on the same procedure.

  • A technical rating still needs parameters that say whether a name is favorable and by how much, so any name can be compared and ranked against another.
  • The case-study rating combines a one-year linear-regression slope, a 12-week higher-high flag, and a 12-week higher-low flag, then maps those flags onto a five-star score.
  • A still-positive slope with both higher highs and higher lows is read as uptrend confirmation, while a swing against a still-intact opposite slope is read as an early turn warning.
  • Weight-swap simulations found lows more important than slope and highs comparably important, contrary to the initial assumption that highs should be down-weighted.
Entries in this reading3 entries
Current trackRuns test19 readingsContrarian strategy26 readingsMomentum strategy103 readings

Why a rating has to rank names

A technical rating still needs parameters that say whether a name is favorable and by how much, so any name can be compared and ranked against another. The case-study rating combines three inputs: a one-year linear-regression slope, a 12-week higher-high flag, and a 12-week higher-low flag.

The one-year slope is kept as a slow trend detector so ordinary pullbacks do not reverse the trend component, at the cost of lag at turning points. The high and low checks are a runs test: a sequential count of higher highs or higher lows over a fixed sampling window, compared across alternative lookbacks as an explicit quantitative baseline.

How slope and swing flags are read

A still-positive slope together with both higher highs and higher lows is read as confirmation of the uptrend. That stay-with-trend reading is the momentum strategy: a rating-based signal that stays with the prevailing trend when a long slope and sequential higher-high or higher-low flags agree.

While the slope remains positive, lower highs are read as an early reverse warning. While the slope remains negative, higher lows are read as an early start-of-uptrend warning. That early-warning reading is the contrarian strategy: a rating-based signal that treats an early swing against a still-intact opposite slope as a turn warning rather than waiting for the slow trend measure to flip.

A five-star map and one cutoff

The three flags are mapped onto a five-star score with initial weights of two stars for slope, one star for higher highs, and two stars for higher lows. The documented procedure buys when the composite is above 2.5 stars and sells when it is below 2.5 stars, on weekly bars from January 2005 through December 2016 across a 100-name large-cap list, versus a broad-index buy-and-hold benchmark.

Trigger levels were stepped by 0.5 stars, and the case study treated 2.5 as a reasonable operating cutoff after inspecting reward-to-risk and percent profitable.

Weight swaps and lookback sweeps

Three weight-swap simulations underweighted highs, slope, or lows in turn. The case study found lows more important than slope and highs comparably important, contrary to the initial assumption that highs should be down-weighted.

The sequential high and low lookback was swept from 4 to 20 weeks and peaked near 12 weeks, which the case study notes equals one quarter. Slope length was swept from 20 to 60 weeks and a 40-week window was treated as a reasonable one-year setting.

Educational research material, not investment advice. Historical source context does not establish present-day performance.
14 of 15 in the Runs test track
20186-7 pp.Next on Runs testRegime-dependent odds after directional price runsA directional run resets to zero when a close prints opposite the prior day and grows only while later closes keep the same sign.
All readings on this track · 15 readings
  1. 1986Constructing runs and persistence tests from labeled prices
  2. 1986Evaluating daily price and volume serial independence windows
  3. 1986Evaluating advance-decline plus-day runs against chance baselines
  4. 1986Weekly resamples as a diagnostic filter for statistical windows
  5. 1988Runs test as a critique of price-series memory
  6. 1989Evaluating weekday close direction with a counted baseline
  7. 1989Statistical windows for indicator time parameters
  8. 1992Channel-height ratios for equity trend evaluation
  9. 2001A runs test before volatility and expected-value sizing
  10. 2005Constructing runs-test z-scores for signed return persistence
  11. 2005Evaluating persistence with runs and autocorrelation
  12. 2005Weekday FX turning points and close run tests
  13. 2013Constructing a runs-test turn forecast
  14. 2017Star rating from slope and swing runs
  15. 2018Regime-dependent odds after directional price runs
By fieldTrend and mean reversion93 readingsBy year2017100 readings
All 19 readings tagged Runs test
Also on Runs test5 readings
1986Constructing runs and persistence tests from labeled prices1986Evaluating advance-decline plus-day runs against chance baselines1986Evaluating daily price and volume serial independence windows1986Weekly resamples as a diagnostic filter for statistical windows1987Evaluating money-supply serial dependence before a forecast