On Predicting the Future, Redux

From a reader, ptuomov:

If you run a regression of the magenta line on variables that have similar trends, you will get a spuriously high R2. I think you should try to explain the weekly changes in the magenta series instead. (I may have misunderstood you regression, in which case please show the actual data series in the regression so I’ll understand it better.)

Um, that’s not always true.  I did not get a Ph. D., but I passed my Ph. D. field in econometrics, including passing the oral exam.  I try to be really careful with regressions, unlike most.  I avoid multiple passes over the data, and I avoid “specification searches,” which are glorified hunts for correlations.

As it is, the regressors that I used are not highly correlated with each other.  They don’t have similar trends.  Here is the correlation matrix:

The regressors were very different variables, and were independently useful for deciphering the relationship.  Had it been otherwise, the t-coefficients would have weak, with the F-coefficient strong.  As it was, the t-coefficients were all strong.

This is not spurious.




About the Author

David Merkel
David J. Merkel, CFA, FSA — 2010-present, I am working on setting up my own equity asset management shop, tentatively called Aleph Investments. It is possible that I might do a joint venture with someone else if we can do more together than separately. From 2008-2010, I was the Chief Economist and Director of Research of Finacorp Securities. I did a many things for Finacorp, mainly research and analysis on a wide variety of fixed income and equity securities, and trading strategies. Until 2007, I was a senior investment analyst at Hovde Capital, responsible for analysis and valuation of investment opportunities for the FIP funds, particularly of companies in the insurance industry. I also managed the internal profit sharing and charitable endowment monies of the firm. From 2003-2007, I was a leading commentator at the investment website RealMoney.com. Back in 2003, after several years of correspondence, James Cramer invited me to write for the site, and I wrote for RealMoney on equity and bond portfolio management, macroeconomics, derivatives, quantitative strategies, insurance issues, corporate governance, etc. My specialty is looking at the interlinkages in the markets in order to understand individual markets better. I no longer contribute to RealMoney; I scaled it back because my work duties have gotten larger, and I began this blog to develop a distinct voice with a wider distribution. After three-plus year of operation, I believe I have achieved that. Prior to joining Hovde in 2003, I managed corporate bonds for Dwight Asset Management. In 1998, I joined the Mount Washington Investment Group as the Mortgage Bond and Asset Liability manager after working with Provident Mutual, AIG and Pacific Standard Life. My background as a life actuary has given me a different perspective on investing. How do you earn money without taking undue risk? How do you convey ideas about investing while showing a proper level of uncertainty on the likelihood of success? How do the various markets fit together, telling us us a broader story than any single piece? These are the themes that I will deal with in this blog. I hold bachelor’s and master’s degrees from Johns Hopkins University. In my spare time, I take care of our eight children with my wonderful wife Ruth.