Model Flashes US Recession Warning: 02-01-2016

The following article updates the diffusion index, recession slack index, aggregate recession model, and aggregate peak-trough model through January 2016. Throughout 2015, I added a number of new economic and market-based variables with very strong explanatory power to the recession model. This allowed me to cull three of the original independent variables with the weakest historical performance and most questionable cause and effect recessionary influence. The current 20-variable model has a diverse set of explanatory variables and is quite robust.

Each of the explanatory variables has predictive power individually; when combined together, the group of indicators is able to identify early recession warnings from a wide range of diverse market-based, fundamental, technical, and economic sources. After the latest additions and deletions, the total number of explanatory recession model variables is now 20. The current and historical data in this report reflect the current model configuration with all 20 variables.

Diffusion Index

The Trader Edge diffusion index equals the percentage of independent variables indicating a recession.  With the recent changes, there are now a total of 20 explanatory variables, each with a unique look-back period and recession threshold. The resulting diffusion index and changes in the diffusion index are used to calculate the probit, logit, and neural network model forecasts.

The graph of the diffusion index from 1/1/2006 to 02/1/2016 is presented in Figure 1 below (in red - left axis). The gray shaded regions in Figure 1 below represent U.S. recessions as defined (after the fact) by the National Bureau of Economic Research (NBER). The value of the S&P 500 index is also included (in blue - right axis).

In December 2014, for the first time since December 2012, one of the 20 explanatory variables indicated a recessionary environment. The number of variables indicating a recession varied between zero and one from December 2014 through May 2015 and between one and two from June 2015 through November 2015. The number of variables indicating a recession jumped from two in November, to five in December, to seven in January 2016. Seven out of 20 explanatory variables (35%) are now indicating a recession which is the highest diffusion index value since the end of of the Great Recession.

The diffusion index remained positive throughout most of 2015, which was troubling. The large spike to seven (35%) in January is much more serious. Going back to 1959, diffusion index readings of 35% have always been associated with U.S. recessions. In other words, the diffusion index has only reached a level of 35% shortly before, during, or after NBER recessions.

In non-recessionary environments, weakness typically persists for a few months and then dissipates.  However, if the weakness becomes more widespread or lingers for many months, that can be more problematic. The weakness persisted throughout much of 2015 at a relatively modest level, but now exceeds past recessionary levels. We have now reached the tipping point.

Please note that past estimates and index values will change whenever the historical data is revised.  All current and past forecasts and index calculations are based on the latest revised data from the current data set.

Figure 1: Diffusion Index 02-01-2016

Figure 1: Diffusion Index 02-01-2016

Recession Slack Index

The Trader Edge recession slack index equals the median standardized deviation of the current value of the explanatory variables from their respective recession thresholds.  The resulting value signifies the amount of slack or cushion relative to the recession threshold, expressed in terms of the number of standard deviations.

The gray shaded regions in Figure 2 below represent U.S. recessions as defined (after the fact) by the NBER.  The median recession slack index is depicted in purple and is plotted against the right axis, which is expressed as the number of standard deviations above the recession threshold.

The dark-red, horizontal line at 0.50 standard deviations denotes a possible warning threshold for the recession slack index.  Many of the past recessions began when the recession slack index crossed below 0.50.  Similarly, many of the past recessions ended when the recession slack index crossed back above 0.0.

In mid-2014, the revised median recession slack index peaked at 1.23, far above the warning level of 0.50. The revised values of the recession slack index declined alarmingly to 0.72 in March 2015, perilously close to the early warning level of 0.50.The median recession slack index then rebounded, and remained between 0.88 and 0.94 from April through July 2015, and between 0.78 and 0.84 from August through November 2015. In December 2015, the slack index dropped to 0.69 and fell even more sharply in January to 0.39, penetrating the warning level of 0.50 for the first time since the Great Recession.

The ability to track small variations and trend changes over time illustrates the advantage of monitoring the continuous recession slack index in addition to the diffusion index above, which moves in discrete steps.

While it is useful to track the actual recession slack index values directly, the values are also used to generate the more intuitive probit and logit probability forecasts.

Figure 2: Median Recession Slack Index 02-01-2016

Figure 2: Median Recession Slack Index 02-01-2016

Aggregate Recession Probability Estimate

The Trader Edge aggregate recession model is the average of four models: the probit and logit models based on the diffusion index and the probit and logit models based on the recession slack index.  The aggregate recession model estimates from 1/1/2006 to 02/01/2016 are depicted in Figure 3 below (red line - left vertical axis).  The gray shaded regions represent NBER recessions and the blue line reflects the value of the S&P 500 index (right vertical axis).  I suggest using a warning threshold of between 20-30% for the aggregate recession model (green horizontal line).

The aggregate recession model probability estimate for 02/01/2016 increased from 3.6% in December 2015 to 21.4% in January 2016. According to the model, the probability that the U.S. is currently in a recession has jumped significantly and is now material.

Figure 3: Aggregate Recession Model  02-01-2016

Figure 3: Aggregate Recession Model 02-01-2016

Aggregate Peak-Trough Probability Estimate

The peak-trough model forecasts are different from the recession model.  The peak-trough models estimate the probability of the S&P 500 being between the peak and trough associated with an NBER recession.  The S&P 500 typically peaks before recessions begin and bottoms out before recessions end.  As a result, it is far more difficult for the peak-trough model to fit this data and the model forecasts have larger errors than the recession model.

The Trader Edge aggregate peak-trough model equals the weighted-average of nine different models: the probit and logit models based on the diffusion index, the probit and logit models based on the recession slack index, and five neural network models.

The aggregate peak-trough model estimates from 1/1/2006 to 2/01/2016 are depicted in Figure 4 below, which uses the same format as Figure 3, except that the shaded regions represent the periods between the peaks and troughs associated with NBER recessions.

The aggregate peak-trough model probability estimate for 02/01/2016 was 48.6%, which is up sharply (+19.6%) from the revised value of 29.0% at the end of December 2015.  The value of 48.6% was (by far) the highest reading since the end of the Great Recession. The aggregate peak-trough model probability estimate of 48.6% exceeds the suggested early warning threshold of 40%.

Figure 4: Aggregate Peak-Trough Model 02-01-2016

Figure 4: Aggregate Peak-Trough Model 02-01-2016

Conclusion

January 2016 marked a potential tipping point in U.S. recession risk. The latest diffusion index reading of 35% has now reached past recessionary levels. Going back to 1959, diffusion index readings of 35% have always been associated with U.S. recessions.

The use of several market-based indicators makes the Trader Edge recession model more responsive than many other models. Relative to traditional economic variables, market-based data have important advantages: they are highly predictive, they are never restated, and there is no lag in receiving the data. The seven diffusion index variables above their recession thresholds at the end of January include market-based and non-market-based data.

Unfortunately, the weakness is not limited to the diffusion index. The latest median recession slack index value of 0.39 has also penetrated its early warning threshold (0.50). In addition, the slack index value of 0.39 represents the lowest reading since the end of the Great Recession. Similarly, the probability that the U.S. is currently in a recession jumped to 21.4% in January, which was the highest reading since the end of the Great Recession. While the 21.4% reading is still below its warning level of 30%, the 30% warning threshold is somewhat arbitrary and could arguably be set even lower. Finally, the peak-trough recession probability estimate increased sharply again in January 2016, ending the month at 48.6%.  Again, this was easily the highest reading since the end of the great Recession and was materially above its early warning threshold of 40%.

Most of the above readings are at or above past recessionary levels. While these values are indicative of a U.S. recessionary environment, the probabilities remain (marginally) below 50%. An imminent U.S. recession is not a certainty, but the risk has grown alarmingly and is now very significant. Given that the equity market was significantly over valued entering this period and the fact that corporate earnings have declined for three consecutive quarters, the downside risk is significant.

Unlike human prognosticators, the Trader Edge recession model is completely objective and has no ego. It is not burdened by the emotional need to defend past erroneous forecasts and will always accurately apply the insights gained from new data. As a result, if the explanatory data reverses direction over the next few months, the recession probabilities will drop accordingly. Conversely, if the contagion continues to spread to the remaining explanatory variables, the recession model will objectively quantify the increased recession risk. It could be a wild (but interesting) ride - stay tuned.

Print and Kindle Versions of Brian Johnson's 2nd Book are Available on Amazon (75% 5-Star Reviews)

Exploiting Earnings Volatility: An Innovative New Approach to Evaluating, Optimizing, and Trading Option Strategies to Profit from Earnings Announcements.

Print and Kindle Versions of Brian Johnson's 1st Book are Available on Amazon (79% 5-Star Reviews)

Option Strategy Risk / Return Ratios: A Revolutionary New Approach to Optimizing, Adjusting, and Trading Any Option Income Strategy

Trader Edge Strategy E-Subscription Now Available: 20% ROR

The Trader Edge Asset Allocation Rotational (AAR) Strategy is a conservative, long-only, asset allocation strategy that rotates monthly among five large asset classes. The AAR strategy has generated annual returns of approximately 20% over the combined back and forward test period.  Please use the above link to learn more about the AAR strategy.

Feedback

Your comments, feedback, and questions are always welcome and appreciated.  Please use the comment section at the bottom of this page or send me an email.

Referrals

If you found the information on www.TraderEdge.Net helpful, please pass along the link to your friends and colleagues or share the link with your social or professional networks.

The "Share / Save" button below contains links to all major social and professional networks.  If you do not see your network listed, use the down-arrow to access the entire list of networking sites.

Thank you for your support.

Brian Johnson

Copyright 2016 - Trading Insights, LLC - All Rights Reserved.

Share

About Brian Johnson

I have been an investment professional for over 30 years. I worked as a fixed income portfolio manager, personally managing over $13 billion in assets for institutional clients. I was also the President of a financial consulting and software development firm, developing artificial intelligence based forecasting and risk management systems for institutional investment managers. I am now a full-time proprietary trader in options, futures, stocks, and ETFs using both algorithmic and discretionary trading strategies. In addition to my professional investment experience, I designed and taught courses in financial derivatives for both MBA and undergraduate business programs on a part-time basis for a number of years.
This entry was posted in Economic Indicators, Fundamental Analysis, Market Commentary, Market Timing, Recession Forecasting Model, Risk Management and tagged , , , , , , , , . Bookmark the permalink.

Leave a Reply

Your email address will not be published. Required fields are marked *