Chris Ridder's  Instablog

I came across this list on another blog; I don't agree with all of them but still an excellent resource!

www.ritholtz.com/blog/2011/09/tbps-30-mo.../

Tomorrow the Labor Department releases the monthly employment report (Non Farm Payrolls - NFP) which is arguably the most anticipated report coming out each month. About 2 weeks ago I came across this chart on a blog, with some hyperbole in the title, about a very large negative NFP number possibility because of the large decline in the Philly Fed Survey.


Source: Bloomberg via http://www.zerohedge.com/news/scariest-chart-ever-philly-fed-versus-non-farm-payrolls

This led me to start researching some econometric models to forecast a possible distribution of outcomes in the NFP number. I also looked at other economic reports that would have august data available. I found that the Philly Fed Survey, Dallas Fed Survey (lagged), 4 week average of job claims (change from month ago), and the  differences lagged of the NFP were significant. This is correlation matrix table is for data from June 2004 to July 2011, and the correlation critical value at the 99% level is approximately .283. One can see that all variables are statically significant.

Philly	NFP	NFP-1	NFP-2	Dallas -1
1	0.5974	0.553	0.507	0.6479	Philly
	1	0.6889	0.6967	0.8047	NFP
		1	0.689	0.8144	NFP-1
			1	0.7911	NFP-2
				1	Dallas -1

I ran a multivariate regression, using HAC standard errors, and received the following results:

	Coefficient	std. error	t-ratio	p-value
constant	-51.3032	18.9197	-2.712	0.0082
dallas_1	3.79735	1.10702	3.43	0.001
d_claims	-0.00252297	0.00052	-4.85	6.09E-06
philly	2.629	1.05501	2.492	0.0148
nfp_d_1	0.373798	0.107461	3.478	0.0008
nfp_d_2	0.207402	0.066711	3.109	0.0026

The coefficient of determination (Adjusted R^2) was 84.4% and the Standard error was 111.75.

(Need help understanding  statistics http://en.wikipedia.org/wiki/Statistics)

Plugging in the data for August, this "model" gives a point estimate of -42,773 of jobs created. Now the current consensus estimate for this report is + 60,000 jobs created as reported by Bloomberg (although there is a report that Goldman cut its estimate today). The range of estimates is from -5,000 to +150,000.

I then made a statistical estimation of the probability values of various scenarios using the point estimate and the standard error.

Above +150,000 = 4.2%
Above +60,000 = 17.9%
Above Zero (no job creation) = 35.1%
Below = -5,000 = 63.2%


This data shows a much greater likely hood of a downside surprise when the NFP report is released. What could be wrong here? First, I don't like the constant being statically significant, in academic circles it should not be. Second I downloaded the NFP data from theSt. Louis Fred but it might be revised data and would introduce a bias. I tried using the Alfred data, and received significant results, but there were large jumps in the data also which appeared not much different from the most popular NFP data.

Here is how this model performed running the regression from June 2004 until January 2009 and then forecasted into the future.






Bottom line this is not a tool for gambling a trade on until it proves itself in real time, and often at that. However, it does make me shift more time to thinking through what I will do if a "bad" employment number is reported.

I will try and update the model more over the next month and see how it does plugging in other data series, such as the ISM data. But for the time being, statistics clearly show a downside surprise is more likely. Get your trading plans ready!


(Any Quant's out there please let me and other readers know if there is a mistake I made.  :-)  Software used was free from http://gretl.sourceforge.net/ )

Disclosure: I have no positions in any stocks mentioned, and no plans to initiate any positions within the next 72 hours.

Additional disclosure: Past erformance is not indicative of future results. Just askthe statistical quant managers at AIG!!! (no position)

This report was just posted on the blog Zerohedge:

It quotes the Ontario Securities Commission as follows:

"Sino-Forest, through its subsidiaries, appears to have engaged in significant non-arm’s length transactions which may have been contrary to Ontario securities laws and the public interest;

Sino-Forest and certain of its officers and directors appear to have misrepresented some of its revenue and/or exaggerated some of its timber holdings by providing information to the public in documents required to be filed or furnished under Ontario securities laws which may have been false or misleading in a material respect contrary to section 122 or 126.2 of the Act and contrary to the public interest;

Sino-Forest and certain of its officers and directors including Chan appear to be engaging or participating in acts, practices or a course of conduct related to its securities which it and/or they know or reasonably ought to know perpetuate a fraud on any person or company contrary to section 126.1 of the Act and contrary to the public interest;"

 

A Reuters report states, "The OSC ordered all trading in Sino-Forest securities to cease and ordered several executives to resign, though it rescinded that order." Trading is still suspended and the stock closed yesterday at 4.81 on the Toronto exchange. So the rescind order must only apply to the executives. Still it is disturbing that such an order was made in the first place.


I had these following lessons to learn for a trader/investor from this situation in a post I wrote in  June:

1. Mistakes and errors happen even to the very successful            (John Paulson owned the company)
2. Getting out at $3 is better than Zero; or cut the losses of a bad trade/investment the best you can                                          (Paulson got out)
3. Muddy Waters had a thesis that "... Harvard-educated Chinese analysts based in New York usually have little more in common with Chinese company managers than you do. As a result, many sub-par Chinese companies find ways to game the system and trade at inflated values." that appears to have (change that to has)  beaten Wall Street "Due Diligence"; so don't abandon sound thinking in front of entrenched and powerful "conventional wisdom".

There are some links at the bottom of the zero hedge post that shows large investors still buying into the stock even after the original report was released. Goes to show, that being large and having money does not always equate to being right.




Disclosure: I have no positions in any stocks mentioned, and no plans to initiate any positions within the next 72 hours.