In my prior post, describing the August, 2009, performance of the Dynamic Trading Risk Factor, I alluded to the fact that the source data, the Barclay Hedge hedge fund indices, does not accrue atomically — in fact it is gradually updated during the course of each month.

In prior posts, I pointed out that the final month's factor return is mostly little changed from that computed from earlier, incomplete, data. As it should be, if the Law of Large Numbers is working it's usual magic. However, nature is often a little more subtle than that, and mankind often deliberately so. It therefore falls to us to ask whether there is any bias between the latency of a given fund's publication of its performance numbers and that same fund's performance relative to the mean of all reporting funds? Our strong prior is that human frailty would lead the bearers of good news to rush it out as soon as possible; and, in contrast, the bearers of bad news to wait a little longer than they should before revealing their shame.

The above chart illustrates my attempt to quantify this effect on the September, 2009, data, which represents the aggregated reported August, 2009, returns of around 2,500 funds as reported during the month. Not possessing an inside track at the data vendor, I had to resort to archiving and timestamping sampled copies of the cumulatively reported data. Thus, it was tedious to collect. Exhibited above is the mean relationship between the relative error in the Hedge Fund Index's reported average return and the relative proportion of the total number of funds that had reported at that time. (In both cases, relative means relative to the final sample value I have for that month's datum.) From this sample there does appear to be a very strong negative correlation, confirming our cynical prior from the earlier paragraph. Unfortunately, the serial correlation of the errors complicates a statistical analysis of the goodness of fit — but by eye it appears excellent.

As of this morning, a total of 2,077 of approximately 2,500 hedge funds have reported data for August, 2009; a little later than previously, it's now time to update our data and forecasts for the dynamic trading risk factor. This gives us an estimate of a number that is not much likely to change during the rest of the month.

Out-of-sample, our final forecast of the return for August, 2009, was 1.68% (our early forecast was 1.97%), and the realization was a 1.87%. Hedge funds are continuing to grow out of their catastrophic drawdown, and we expect this to continue, so we are forcasting a 1.11% final return for September, 2009. These forecasts represent an a priori expected monthly return for any fund or firm that makes it's living by trading.

The Compact Model Portolio, which has been quiescent for a long time, has traded again. This time substituting J.P. Morgan (JPM) for Wells Fargo (WFC). (The history of the composition of this index, and it's daily return relative to the benchmark, is available on the blog side panel.)

On 10th. February, 2006, I performed the analysis repeated in this post, and also on an earlier post on this blog, looking at the cumulative kurtosis of the daily changes in interest rates. Not knowing what to do with the analysis, but concerned about it's possible implications, I considered writing a letter to the Director of Research at the Federal Reserve but, in the end, I sent a fax to James Grant, editor of Grant's Interest Rate Observer, and a noted skeptic of the glory of centrally planned monetary policy.

In my letter I wrote:

“During the last 20 years the Fed has made everybody happy by bringing down the volatility of interest rates but we appear to have paid for this by obtaining a distribution of daily changes substantially more prone to extreme variation; or, to put this a little more colourfully, that the animal spirits of interest rates have not been tamed but have undergone a metamorphosis from prowling tom cat to sleepy tiger.” Graham Giller, 02/10/2006.

Mr. Grant liked my ‘tom cat/tiger,’ imagery, but I feel I didn't fully convince him of my main point — that, by supressing the standard deviation in exchange for a badly controlled kurtosis, policy was running towards an extreme event that would be truly off-the-charts. However, the purpose of this post is not to claim some magical ex-ante call for the decline of western finance as we knew it. It is to re-examine these metrics and see, in the same manner as before, what story they're telling us.

So let us examine the tail end of the kurtosis curve in the above chart. This shows how the cumulative sample kurtosis of the one day change in the yield of U.S. three month treasury bills has been accumulating as each day of the Ben Bernanke tenure as Chairman of the Board of Governors of the Federal Reserve System.

The malfunction of the U.S. financial markets, as indicated by the momentary pause in the upward ascent of the cumulative kurtosis, appears to have started after the kurtosis peaked at 30.06 on 08/08/2007 and ended after it had drawn down to 28.50 on 10/30/2008. The dates we have estimated for the crisis in the performance of hedge funds, based on our monthly data series of the returns due to the dynamic trading risk factor (which is extracted from the returns of hedge funds, are 10/2007 to 11/2008. Since then it has been steadily marching upwards again, although it has not yet breached that peak level.

It remains to be seen whether this is indicating that the true population kurtosis is merely higher than the currently observed value, or whether it is entirely unbounded above. But this trend is consistent with the hypothesis that, as far as activity in the interest rate markets is concerned, game is back on!

New data, derived from a sample of 1000 funds, is now available for the Dynamic Trading Risk Factor. Before going into the performance of the factor, which I will do in a following post, I thought I would discuss some changes to the constituency of the Poor Man's Hedge Fund, our a portfolio designed to replicate the performance of hedge funds by investing in the common stocks of firms which have monthly returns well described by the factor.

The table shows the eight members of the XLF benchmark index that have the highest regression R² onto the dynamic trading risk factor. The membership of the portfolio is unchanged, although there has been some reordering in response to the new data. In particular, JNS has dropped out of the top 5 and been replaced by AMP.

At this time, I also decided to change slightly the relative composition of the portfolio. I have been constructing an equal weighted portfolio with 60% of the capital allocated to the member stocks and 40% to the hedge. From now on, those members will be individually weighted by their particular R² relative to the portfolio mean. The changes are actually slight.

It's now three month's since we started trading a portfolio designed to replicate the performance of hedge funds by picking those stocks with maximum exposure to the dynamic trading risk factor.

The portfolio's performance peaked in early August, and has been in a drawdown since then. It was hit hard on the 1st. September, when all the financial stocks dramatically underperformed the market. However, it is still profitable after fees.

UPDATE 03/15/2010: The performance chart has been replaced with the one for this current year. As you can see, the system is currently in a small drawdown.