Sunspot Cycle and Stock Returns

October 21, 2011 • Posted in Calendar Effects, Individual Gurus

A reader asked: “Have you had the opportunity to evaluate Charles Nenner as an equity and commodities forecaster?” Charles Nenner is self-described as “the talk of Wall Street since accurately predicting some of the biggest moves in the Markets over the past few years.” In his July 2007 discussion of the “Nenner Methodology at the Bloomberg Studio”, Charles Nenner cites sunspot activity as a specific key indicator for equity returns. Is there any reliable relationship between sunspot activity and stock market returns? Using monthly averages of daily sunspot counts from the Solar Influences Data Analysis Center and monthly closing levels of the Dow Jones Industrial Average (DJIA) for September 1928 through September 2011 (997 months) and the S&P 500 Index for January 1950 through September 2011 (741 months), we find that:

As background, the referenced presentation summarizes Charles Nenner’s approach to predicting the behavior of financial markets, as follows:

  • Charles Nenner is “a natural pattern recognizer.” His analysis is not a science, it is an art, although it is as complicated as rocket science.
  • He uses three principal tools to analyze financial markets:
    1. A technical model based on about 200 indicators (such as moving averages, put-call ratios, advance-decline ratios, insider sales, up-down volume ratios). This tool generally prevails when his other tools disagree.
    2. Empirical cycles (distances between tops and bottoms) over multiple horizons, refined via Fourier analysis. Cycles are as reliable as airplanes, reflecting consistent human interpretations of events that are impervious to learning. Cycles will always work because politicians and economists do not want to believe that economies are deterministic (and constituents therefore not in need of their services). Longer cycles are generally more powerful than shorter ones. Cycles indicate direction, but not level. Other methods determine level via measuring upward and downward price momentum.
    3. Elliott wave analysis.
  • He believes that the sunspot cycle correlates strongly with equity markets via the predictable effects of magnetic field disturbances on investors. High sunspot activity produces exuberance. The sunspot cycle indicates that the bull market will top in 2013 (per the July 2007 presentation).

The assertion that Dr. Nenner’s work is more art than science suggests that no one can independently and systematically replicate his forecasts. We can, however, test the predictive power of the sunspot cycle for equity market returns. Sunspot populations quickly rise and more slowly fall on an irregular cycle of 11 years.

The following chart compares the monthly average of daily sunspot counts to contemporaneous monthly DJIA closing levels (log scale) over the entire sample period, which comprises roughly 7.5 sunspot cycles. Visual inspection reveals no consistent relationship between the two series.

For a closer look, we compare sunspot activity to monthly changes in DJIA.

The following scatter plot relates DJIA monthly return to the average daily sunspot count during that month over the entire sample period. The Pearson correlation for the two series is -0.03 and the R-squared statistic is 0.001, indicating that variation in monthly average sunspot counts explains practically none of contemporaneous variation in monthly DJIA returns. Results for the S&P 500 Index since 1950 are similar.

Might the monthly change in sunspot count explain future stock market returns?

The next scatter plot relates DJIA monthly return to the month-to-month change in average daily sunspot count for that month over the entire sample period. The Pearson correlation for these two series is -0.04 and the R-squared statistic is again 0.001, indicating that variation in monthly change in sunspot counts explains practically none of contemporaneous variation in monthly DJIA returns. Results for the S&P 500 Index since 1950 are similar.

Might the monthly average of daily sunspot counts or change in sunspot count affect the stock market with a delay?

The next chart plots Pearson correlations for various lead-lag relationships between monthly average sunspot activity and monthly DJIA returns over the entire sample period, ranging from DJIA returns lead sunspot activity by 12 months (-12) to sunspot activity leads DJIA returns by 12 months (12). All correlations are very small for both sunspot count and change in sunspot count, indicating no meaningful lead-lag relationship between sunspot activity and stock market returns.

Might there be a material non-linearity in the relationship between sunspot activity and stock market behavior?

The final two charts summarize average monthly DJIA returns and average monthly S&P 500 Index returns by decile of monthly average sunspot count (upper chart) and by decile of change in monthly average sunspot count (lower chart) over the available sample periods. Each decile consists of about 100 (74) observations for the DJIA (S&P 500 Index). Lack of systematic progressions across deciles and differences between results for the two stock market samples undermine belief in any useful relationship.

In summary, evidence from an array of simple tests does not support belief in a reliable relationship between sunspot activity and stock market returns.

Some other aggregation of daily sunspot counts might produce different results.

Why not subscribe to our premium content?
It costs less than a single trading commission. Learn more here.
Login
Current Momentum Winners

ETF Momentum Signal
for April 2014 (Final)

Momentum ETF Winner

Second Place ETF

Third Place ETF

Gross Momentum Portfolio Gains
(Since August 2006)
Top 1 ETF Top 2 ETFs
217% 197%
Top 3 ETFs SPY
197% 68%
Strategy Overview
Recent Research
Popular Posts
Popular Subscriber-Only Posts