Objective research and reviews to aid investing decisions
 Looking for information on debt consolidation loans? Want to know more about reverse mortgages? |
A reader suggested that we review the stock market commentary of Mark Hulbert, editor of the Hulbert Financial Digest and Hulbert Interactive, both of which track the recommendations of a wide range of investing newsletters. Mr. Hulbert is also a regular columnist at MarketWatch.com. Because Mr. Hulbert uses his Hulbert Stock Newsletter Sentiment Index (HSNSI) as a principal quantitative tool in formulating his market outlook, we evaluate the usefulness of that index in predicting stock market returns rather than his qualitative commentary. HSNSI "reflects the average recommended stock market exposure among a subset of short-term market timers tracked by the Hulbert Financial Digest." Mr. Hulbert regards HSNSI as a contrarian signal for future stock returns; when HSNSI is high (low), he views the outlook for stocks as generally bearish (bullish). Using a sample of 169 values of HSNSI over the period 7/22/02-1/28/08 (generated by searching MarketWatch.com for "HSNSI" and its predecessor "HSSI"), we find that:
The average value of HSNSI for the sample is 27.7%, with a standard deviation of 23.4% (very high volatility). The high for the sample is 67.8%, and the low is -30.6%. In terms of size alone, the sample is large enough to test predictive power with reasonable reliability for short-term stock returns (a few trading days or weeks), but is not large enough to test HSNSI reliably as a long-term stock market indicator. The sample is very likely biased due to selection and clustering around extreme values, because Mr. Hulbert is more likely to cite HSNSI, and cite it frequently, when it is very high or very low. We address these probable biases later.
The following chart superimposes the HSNSI sample on a plot of the S&P 500 index. The blue dashed line is the average HSNSI for the sample. As noted, HSNSI has high variability. Over the sample period, HSNSI tends to rise gently, perhaps because the stock market has been generally advancing. Visual inspection suggests that HSNSI, like many other sentiment indicators, might tend to be high (low) during market peaks (dips).
To add precision to that observation, we examine how HSNSI relates to changes in the S&P 500 index.
The following scatter plot relates the return on the S&P 500 index over the next five trading days (one week) to HSNSI. It shows a negative relationship, as inferred by Mark Hulbert. The Pearson correlation for the two series is -0.31, indicating some tendency for the stock market to rise (fall) over the next five trading days when HSNSI is low (high). The R-squared statistic suggests that HSNSI explains about 10% of stock price movement over the next five days. Note that the sample still has the original selection/clustering biases at this point. Clustering leads to modest overlap of five-day test intervals, effectively reducing sample size and perhaps overweighting extreme values of HSNSI.
The next scatter plot relates the return on the S&P 500 index over the next 21 trading days (one month) to HSNSI. It also shows a negative relationship. The Pearson correlation for the two series is -0.29, indicating some tendency for the stock market to rise (fall) over the next 21 trading days when HSNSI is low (high). The R-squared statistic suggests that HSNSI explains about 8% of stock price movement over the next 21 days. Note that the sample still has the original selection/clustering biases at this point. Clustering leads to moderate overlap of 21-day test intervals, effectively reducing sample size and perhaps overweighting extreme values of HSNSI.
The third scatter plot relates the return on the S&P 500 index over the next 63 trading days (three months) to HSNSI. It again shows a negative relationship. The Pearson correlation for the two series is -0.43, indicating a tendency for the stock market to rise (fall) over the next three months when HSNSI is low (high). The R-squared statistic suggests that HSNSI explains a notable 18% of stock price movement over the next 63 days. However, selection bias in the sample, along with substantial overlap of 63-day test intervals, have potential to mislead.
Next, we address the selection/clustering biases.
To eliminate test interval overlap and alleviate clustering bias, we winnow sample points so that no two surviving points are within five trading days of each other. The revised sample size is 128 (we deleted 41 closely clustered sample points). Then we order the revised sample from lowest to highest HSNSI and relate the return on the S&P 500 index over the next five trading days to HSNSI. Ordering helps determine whether some ranges of HSNSI might be more predictive than others. The following chart shows the results. Note that the horizontal axis is not time-sequential. The Pearson correlation between the two series is still -0.31, and the R-squared statistic suggests again that HSNSI explains about 10% of stock price movement over the next five days. Some residual selection/clustering biases likely remain.
Visual inspection suggests two return regimes below and above an HSNSI value of about 20%, and that low values of HSNSI may relate to relatively high stock return volatility. In fact, for the 85 (43) instances when HSNSI is greater (less) than 20%, the Pearson correlation between 5-day stock returns and HSNSI is only -0.08 (0.03), and the R=-squared statistic is just 0.008 (0.010). In other words, within the subsample above and the subsample below an HSNSI value of 20%, variation in HSNSI explains practically nothing about stock returns. However, the average return on the S&P 500 index over the next five trading days is 1.4% when HSNSI is below 20%, compared to -0.3% when HSNSI is above 20%. The average five-day return for all days in the winnowed sample is 0.2%.
One interpretation of these results is that low HSNSI relates to periods during which investors are scrambling out of or into the stock market in mass, and there is not enough liquidity to accommodate their correlated (panicky) actions. The modest predictive power arises from the existence of two regimes rather than a consistent linear relationship between HSNSI and future 5-day returns.
To eliminate test interval overlap and alleviate clustering bias for a longer test interval, we winnow sample points so that no two surviving points are within about 21 trading days of each other. The revised sample size is 53. We again order the revised sample from lowest to highest HSNSI and relate the return on the S&P 500 index over the next 21 trading days to HSNSI. The following chart shows the results. The Pearson correlation between the two series is -0.29, and the R-squared statistic is 0.08. Clustering bias is nearly gone in this case, but some selection bias likely persists.
Visual inspection suggests two return regimes below and above an HSNSI value of about 30%. The average return on the S&P 500 index over the next 21 trading days is 1.9% when HSNSI is below 30% and -0.4% when HSNSI is above 30%. The average 21-day return for all days in the winnowed sample is 0.6%.
Finally, to refine analysis for an even longer test interval, we winnow sample points so that no two surviving points are within about 63 trading days of each other. The revised sample size is down to just 20. We again order the revised sample from lowest to highest HSNSI and relate the return on the S&P 500 index over the next 63 trading days to HSNSI. The following chart shows the results. The Pearson correlation between the two series is -0.17, and the R-squared statistic is just 0.03. These results indicate that HSNSI is probably not useful as an indicator for 63-day stock market returns. Clustering bias is gone in this case, but some selection bias may persist. This case especially would benefit from a longer-duration sample.
HSNSI may be more strongly related to past than future stock returns. The Pearson correlations between HSNSI and S&P 500 index returns over the past 5, 21 and 63 trading days (uncorrected for clustering bias) are 0.20, 0.59 and 0.68, respectively. When the stock market advances (declines), HSNSI tends to rise (fall). For returns over the future 5, 21 and 63 trading days, as noted above, the correlations are -0.30, -0.29 and -0.43. In other words, it may be easier to predict the value of HSNSI based on stock returns from the past month and quarter than it is to predict stock returns for the next month and quarter based on the value of HSNSI.
In summary, the Hulbert Stock Newsletter Sentiment Index may have some predictive power for future stock returns. The available sample suggests that its contrarian signal is most useful for very low values of the index and short-term stock returns.
See Guru Grades for a snapshot of the accuracies of various experts in forecasting the direction of the U.S. stock market, including links to detailed individual evaluations. We do not include Mr. Hulbert in the snapshot because the above review is fundamentally different from the reviews of guru commentaries.
For research on other sentiment indicators, see Blog Synthesis: Sentimental Journey.
