Skip to main content
Track Linear regression
40 / 43
Search the archiveLibrary
Library

2017issue C078-15

Nikkei-yen intermarket divergence as a regime case study

This 2017 case study uses the Nikkei 225 and USD/JPY to show how Intermarket analysis can frame an equity-currency pairing as a market regime. Editorial view: treat Linear regression and Price-indicator divergence as a second step, and test that trigger only while the pairing is still intact.

  • A weaker home-currency exchange rate can make export goods cheaper and more competitive abroad, which is the economic premise used to link Japanese equities with the yen.
  • USD/JPY is the correlation pair because the United States accounted for 20.2% of Japanese exports in 2015, and carry-trade flows can reinforce the same equity-currency link.
  • The pairing is not constant: yearly correlations were weaker or negative in the 1990s, later strengthened under ultra-loose Bank of Japan policy, and can give way to the S&P 500 when panic dominates.
  • Editorial view: a 50-day Linear regression Price-indicator divergence reading is a trigger to test only after checking that the Nikkei-yen regime is still intact.
Entries in this reading3 entries
Current trackLinear regression112 readingsIntermarket analysis136 readingsPrice-indicator divergence142 readings

Why the archive paired the Nikkei with the yen

A weaker home-currency exchange rate can make export goods cheaper and more competitive abroad. That is the economic premise used to link Japanese equities with the yen.

After the June 2016 Brexit vote through early 2017, the British pound fell 18.7% against the US dollar while the FTSE 100 rose 17.2%. The archive presented that move as a contemporaneous equity-currency example of the same export-competitiveness idea.

In 2015 the United States was Japan’s most important export partner, accounting for 20.2% of Japanese exports. That is why USD/JPY is used as the correlation pair for the Nikkei 225.

The yen-equity link is also reinforced by carry-trade mechanics. Optimism tends to fund equity exposure by selling a lower-yielding yen for dollars, while risk aversion forces those trades to be reversed.

What the Nikkei 225 is

The Nikkei 225 is a modified price-weighted index of 225 first-section Tokyo common stocks. In February 2017 Fast Retailing had a 6.95% weight, larger than the 6.55% combined weight of Japanese ADSs trading in New York.

The pairing is a regime, not a constant

A weekly overlay from 2006 to February 2017 shows the Nikkei tracking USD/JPY closely. The archive also notes that the equity-currency relationship can change with interest rates, monetary policy, quantitative easing, earnings, and global conditions.

Yearly correlations were weaker or negative in the 1990s and later strengthened as the yen became a funding currency under ultra-loose Bank of Japan policy. From 2002 through early 2017 the Nikkei-USD/JPY correlation turned negative only in 2003 and 2009, late in those bear markets.

The regression divergence trigger

On a DXJ chart from December 2015 to January 2017, the 50-day regression divergence indicator generated buys when it crossed above 75 and then turned down within three days. It generated shorts when it crossed below 25 and then turned up.

Most backtest profits for the intermarket divergence system clustered in 2011-2015, coinciding with the stronger Nikkei-yen correlation window.

Editorial reading: filter first, trigger second

Editorial view: Intermarket analysis of the Nikkei and USD/JPY is the first question, because the archive itself shows that the pairing can fade with policy, earnings, global conditions, and fear. Linear regression and Price-indicator divergence are the second question: a defined 50-day reading with 75 and 25 crossings.

Editorial view: the backtest clustering inside the stronger correlation window is a reason to ask whether that divergence reading is only useful while the regime is still intact, not a reason to treat the trigger as standalone.

DXJ 50-day regression divergence versus 75/25 signal lines

Shorts cluster only after the oscillator slips under 25 and turns, which is how the December 2015–February 2016 selloff is marked; buys wait for a run through 75 that then rolls over, which is what launches the late-2016 rally. The series is a visual reading of the lower pane on the published DXJ daily chart, using the printed 0–100 scale, the drawn 75 and 25 lines, and the 43 last-value tag.
Shorts cluster only after the oscillator slips under 25 and turns, which is how the December 2015–February 2016 selloff is marked; buys wait for a run through 75 that then rolls over, which is what launches the late-2016 rally. The series is a visual reading of the lower pane on the published DXJ daily chart, using the printed 0–100 scale, the drawn 75 and 25 lines, and the 43 last-value tag.DXJ · daily · 2015-12-01T00:00:00.000Z to 2017-01-31T00:00:00.000Z

Katsanos fixes a 50-day regression window. The published rule buys a close after a 75-break that turns down within three days, and shorts a 25-break that turns up. This pane is the choppy 2016 tail of a 2007–2017 test; most backtest profit accrued in 2011–2015, when Nikkei–yen correlation was strong.

Educational research material, not investment advice. Historical source context does not establish present-day performance.
40 of 43 in the Linear regression track
201747-47 pp.Next on Linear regressionConstructing Calmar ratio and linear regression baselinesThe Calmar ratio is constructed on a monthly sampling interval by dividing average return over the most recent 36 months by maximum drawdown over that same window.
All readings on this track · 43 readings
  1. 1990Constructing dollar baselines from rates, inflation, and residuals
  2. 1990Constructing a nominal index value from forward earnings and fitted yield
  3. 1990Constructing a nominal index price from earnings and a fitted yield
  4. 1990Endpoint-pinned price paths are not forecasts
  5. 1990Constructing least-squares polynomial smoothers
  6. 1991Endpoint growth rates versus linear-regression consistency
  7. 1991Out-of-sample checks for linear growth fits
  8. 1991Trend as persistence, not a straight line
  9. 1991Quadratic trend, residual oscillator, and a secondary cycle calendar
  10. 1991Time-origin offset and residual-price divergence on a quadratic least-squares fit
  11. 1991A least-squares trendline from ordered prices
  12. 1992Constructing log-linear growth and reliability screens
  13. 1992Constructing log-linear growth-rate baselines
  14. 1992Next-session high, low, and close from rolling linear regression
  15. 1993Auditing an index price-earnings multiple with short-rate regression
  16. 1994Regression-seeded nested exponential price filter
  17. 1994Constructing the double exponential average from lag cancellation
  18. 1994Evaluating money supply as a linear leading-index baseline
  19. 1995Constructing least-squares trend channels
  20. 1995Linear baseline holdout checks for annual bill-rate forecasts
  21. 1995Projection bands from high and low regression slopes
  22. 1995Evaluating a least-squares end-point moving average on a known test series
  23. 1996Constructing an endpoint moving average from a least-squares line
  24. 1996Scoring equity path consistency with a k-ratio overlay
  25. 1996Evaluating month-end yield gaps for equity regimes
  26. 1996Constructing session-indexed standard error bands
  27. 1998Evaluating linear regression baselines for index valuation
  28. 1998R-squared as a two-state trend filter from a price-time fit
  29. 2000Second-order moving-average lag correction
  30. 2002Price regression line versus beta for index tracking
  31. 2003Regression slope with an r-squared trend confidence gate
  32. 2003Constructing finite-volume-element divergence with slope comparison
  33. 2004Building a daily score from regression, retracement, and volume
  34. 2004Constructing least-squares trendlines from ordered prices
  35. 2007Rectangle breakout targets beyond height
  36. 2007Confirming a price trend with regression slope and r-squared
  37. 2008A linear-regression angle assembled as one trend filter
  38. 2010A two-state swing machine from four running extremes
  39. 2016Score oil-complex tightness before divergence or regression
  40. 2017Nikkei-yen intermarket divergence as a regime case study
  41. 2017Constructing Calmar ratio and linear regression baselines
  42. 2019Pair-trade layer construction versus average-spread management
  43. 2020A convolution slope built from nested linear regression
By fieldIntermarket and spreads148 readingsBy year2017100 readings
All 112 readings tagged Linear regression
Also on Linear regression5 readings
1990Constructing dollar baselines from rates, inflation, and residuals2016Score oil-complex tightness before divergence or regression1989A precious-metal price as a changing intermarket equation1990Earnings yield, rate correlation and regression for equity value1996Evaluating month-end yield gaps for equity regimes