Disposable Income and the Stock Market
Posted in Economic Indicators
August 19, 2010
A reader asked: “Is disposable income a leading indicator of the stock market?” Arguably, an increase in disposable income would lead to growth in consumption, corporate earnings and stock valuation. The Bureau of Economic Analysis releases seasonally adjusted Disposable Personal Income (DPI) monthly with a lag of about one month via Line 22 of Table 2.6, “Personal Income and Its Disposition, Monthly.” Using this series and S&P 500 Index data for January 1959 through June 2010 (618 months), we find that…
The following chart compares the behaviors of the S&P 500 Index and seasonally adjusted DPI over the entire sample period. Although both series generally rise over time, the large mismatch in volatilities makes it very difficult to discern any tradable relationship between the two series.
For a closer look, we compare monthly changes in the two variables.
The following scatter plot relates the monthly change in the S&P 500 Index to the same-month change in DPI over the entire sample period. The Pearson correlation between the two series is 0.09 and the R-squared statistic is 0.008, indicating that changes in DPI explain roughly 1% of S&P 500 Index returns at a monthly horizon.
Do changes in DPI, as indications of consumer spending potential, reliably lead changes in the stock market?
The next chart shows the Pearson correlations for various lead-lag scenarios between monthly changes in DPI and monthly changes in the S&P 500 Index, ranging from stocks lead DPI by 12 months (-12) to DPI leads stocks by 12 months (12). All correlations are small, and there is no evidence that either series materially leads the other.
What if the relationship is cumulative, visible not with monthly changes but perhaps with quarterly changes?
The next chart shows the Pearson correlations for various lead-lag scenarios between quarterly changes in DPI and quarterly changes in the S&P 500 Index, ranging from stocks lead consumption by six quarters (-6) to consumption leads stocks by six quarters (6). A reasonable interpretation of results is that there is perhaps some tendency for the stock market to lead DPI by one to four quarters in a positive relationship (DPI weakly tends to increase/decrease after a stock market rally/slump), and perhaps a somewhat weaker tendency for DPI to lead the stock market by one to four quarters in a negative relationship (the stock market weakly tends to rally/slump after a decrease/increase in DPI). However, all correlations are small.
As a final test that discovers non-linearity in a relationship, we rank S&P 500 Index returns by lagged changes in DPI.
The final chart shows the S&P 500 Index average monthly return by quintile of monthly change in DPI lagged by two months to avoid using data that would not be available to an investor. For example, the Bureau of Economic Analysis typically releases DPI for January at the end of February, so an investor has the January DPI to make a decision about investing for March. This offset corresponds to that indicated by “2″ in the second chart above.
The chart presents results for the overall sample period (123 instances per quintile) and, as a robustness check, for two equal subperiods (61-62 instances per quintile).
Results suggest that the lower (negative or less positive) changes in DPI, as announced, indicate relatively strong stock market returns the following month (the average monthly return for all months in the sample is 0.6%). However, lack of completely monotonic progression across quintiles and fairly dramatic inconsistencies between subperiods undermine this conclusion. The older half of the sample drives the outperformance of the lowest quintiles. Also, omitting the five strongest stock market months from the 123 in the lowest DPI quintile for the total sample brings that quintile’s average return close to the average for all months.
In summary, evidence from simple tests does not support a belief that changes in Disposable Personal Income usefully predict stock market returns at monthly and quarterly horizons.
You May Also Enjoy...
It costs less than a single trading commission. Learn more here.
