Skip to main content
Track Correlation analysis
30 / 37
Search the archiveLibrary
Library

2018issue C0120-23

Clustered negative troughs in an energy-index pairwise correlation

A 13-week energy-versus-index pairwise-correlation averaged 0.63 and stayed positive overall. The case study treated clustered-negative-troughs, a spacing-filter, and a recovery-clock as one procedure, including when to stand aside.

  • The energy-versus-index pairwise-correlation averaged 0.63 with a standard deviation of 0.34, remained positive overall, and did not line up one-for-one with the index close.
  • Clustered-negative-troughs fewer than 25 weeks apart were recorded as later index-top cases. Two wider-spaced pairs were recorded as false positives under the spacing-filter.
  • A recovery-clock measured the index's largest decline over the next 52 weeks from the second trough, the later zero cross, or the later 0.5 cross.
  • The setup was one procedure with regime-abstention when the troughs were more than 25 weeks apart. The March-June 2017 path was treated as outside the earlier sample pattern.
Entries in this reading2 entries
Current trackCorrelation analysis52 readingsSeasonal trading60 readings

A positive average that is still only context

The study built a 13-week pairwise-correlation from weekly adjusted closes of an energy-sector fund and a broad S&P 500 fund. The pair was one case in a sector-by-sector series.

On the plotted history that pairwise-correlation averaged 0.63 with a standard deviation of 0.34 and remained positive overall. Its level did not line up one-for-one with the index close.

Clustered negative troughs and the spacing filter

Selected episodes with two negative correlation troughs fewer than 25 weeks apart were aligned with later index peaks and subsequent declines. Those clustered-negative-troughs included 2000, 2006-2007, and 2014.

Every pair of negative troughs less than 52 weeks apart from January 2000 through June 2017 was collected. Seven paired-trough events entered that table. The five with troughs fewer than 25 weeks apart were recorded as later index-top cases. The two with wider spacing were recorded as false positives under the spacing-filter.

Three recovery clocks on a 52-week window

The index's largest decline over the next 52 weeks was measured from three recovery-clock starts: the second trough, the later move through zero, and the later move through 0.5.

When the two troughs were 25 weeks or closer, the tabulated average 52-week maximum index declines were 12.8% from the second trough, 11.5% from the later zero cross, and 14.1% from the later 0.5 cross. The two wider-spaced cases averaged 0.0%, 0.6%, and 1.9% on the same clocks.

S&P 500 max drop after clustered XLE/SPY correlation troughs

Seven cases of two negative local minima in the 13-week XLE versus SPY correlation, spaced under 52 weeks, show how large a subsequent 52-week S&P 500 drawdown was after the second trough. The five pairs spaced 25 weeks or less average a 12.8% drop; the two wider pairs average about zero. Values are the % MaxDrop since min2 column from the source table (Figure 2).
Seven cases of two negative local minima in the 13-week XLE versus SPY correlation, spaced under 52 weeks, show how large a subsequent 52-week S&P 500 drawdown was after the second trough. The five pairs spaced 25 weeks or less average a 12.8% drop; the two wider pairs average about zero. Values are the % MaxDrop since min2 column from the source table (Figure 2).XLE vs SPY 13-week pairwise correlation; S&P 500 close (SPY) · 13-week correlation; 52-week forward MaxDrop · 2000-06-09T00:00:00.000Z to 2014-12-26T00:00:00.000Z

MaxDrop is the largest S&P 500 close-price decline in the 52 weeks after the second negative correlation minimum. Rows 1–5 are the under-25-week cluster; rows 6–7 exceed 25 weeks and were treated as false positives.

One procedure and a path outside the sample

The write-up specified the setup as one procedure with a chosen recovery-clock, a 52-week observation window, and abstention when the two negative troughs were more than 25 weeks apart.

From March through June 2017 the same series printed two deep negative troughs, including a reading of -0.934 on 17 March 2017 described as an 18-year low, without first recovering through zero. That path was treated as outside the earlier sample pattern.

Educational research material, not investment advice. Historical source context does not establish present-day performance.
30 of 37 in the Correlation analysis track
20187-7 pp.Next on Correlation analysisFilter pairwise-correlation before reading an intermarket regimeUnfiltered time-stamped prices can give misleading pairwise-correlation readings when a random component and time-register-mismatch are left in the series.
All readings on this track · 37 readings
  1. 1988Constructing a lead-aware correlation coefficient
  2. 1989A precious-metal price as a changing intermarket equation
  3. 1990Two clocks for copper: a factor regime, a regression baseline, and leftover moving-average timing
  4. 1990Earnings yield, rate correlation and regression for equity value
  5. 1991Name the window, then combine leaders
  6. 1991Constructing a two-market linear correlation check
  7. 1991Constructing a commodity-bond correlation regime filter
  8. 1992Building intermarket context with linear correlation
  9. 1993Inverse-scale overlays as a gold-equity regime filter
  10. 1994Constructing seasonal slots from windows, analog years, and implied volatility
  11. 1995Pin one reference close and roll companion correlations as an overlay
  12. 1995Rolling correlation windows for shifting intermarket regimes
  13. 1998Gold as a cross-market regime barometer
  14. 1999The gold-bond inverse is a regime, not a cause
  15. 1999A nested lag test of gold leading bond yields
  16. 1999Constructing spreads from stock and intermarket correlation
  17. 2000Evaluating headline versus food-and-energy-excluded CPI as bond-yield context
  18. 2005A late EUR/USD fifth wave tested by the Bund-Treasury gap
  19. 2006Intermarket dislocation as context for short-horizon momentum
  20. 2008Map ordinary 12-month outcomes before stacking valuation, rates, and seasonality
  21. 2008A clean-energy theme inside the oil-and-energy regime
  22. 2014Quantitative-easing overlays as fragile belief regimes
  23. 2015Three intermarket checks from the late-2014 crude decline
  24. 2015Basket construction via rank, correlation, and locked rules
  25. 2015Construct a CAD-oil pair from percent-of-range Bollinger maps
  26. 2015CAD/USD and crude: first the correlation, then the band gap
  27. 2017Correlation regime versus moving-average crossover for S&P 500 exposure
  28. 2017Updating intermarket systems after correlation shifts
  29. 2017Constructing a correlation-divergence regime filter for yen and Nikkei context
  30. 2018Clustered negative troughs in an energy-index pairwise correlation
  31. 2018Filter pairwise-correlation before reading an intermarket regime
  32. 2018Moving-average supports in the March 2018 correlation shock
  33. 2020Bond spreads as an equity regime lens
  34. 2020Crash-protection folklore as a correlation regime question
  35. 2020Constructing a bounded correlation-trend-filter
  36. 2020Constructing a correlation-to-line trend filter
  37. 2020Bitcoin correlation regimes across equities and gold
By fieldIntermarket and spreads148 readingsBy year201898 readings
All 52 readings tagged Correlation analysis
Also on Correlation analysis5 readings
1988Building consensus indicators with correlation and the chi-square test1988Constructing a lead-aware correlation coefficient1989A precious-metal price as a changing intermarket equation1990Two clocks for copper: a factor regime, a regression baseline, and leftover moving-average timing1990Earnings yield, rate correlation and regression for equity value