The Big Picture - Macro Perspective on the Capital Markets, Economy, Technology, and Digital Media

Another Dilbert lesson on Correlation:
>

>
Classic !

Barry has been crushing the BLS flat-earthers the past few days.

Resistance, however, is futile.  Try as I might not to opine on the 1.2-million-one-month-drop-in-the-labor-force, I cannot help but spill a few pixels of my own.  So here goes.

Let’s start with last month’s BLS Employment Situation release.  It contained a box, on Page 4 (of the PDF), that included the following heading and text (emphasis mine):

Upcoming Changes to the Household Survey

Effective with the release of The Employment Situation for January 2012 scheduled for February 3, 2012, population controls that reflect the results of Census 2010 will be used in the monthly household survey estimation process. Historical data will not be revised to incorporate the new controls; consequently, household survey data for January 2012 will not be directly comparable with that for December 2011 or earlier periods. A table showing the effects of the new controls on the major labor force series will be included in the January 2012 release.

So right there, in black and white, BLS explicitly told its users that January 2012 and December 2011 (and earlier) simply would not be comparable — and that would obviously be the case notwithstanding how the various numbers broke.

Overlooking that caveat is one thing, I guess.  Being corrected all over the web and then not correcting and/or retracting is something else altogether.

ADDING:  For what little I’m sure it’s worth, whenever I have had a question about an economic release — and that’s dozens (hundreds?) of times — I have picked up the phone and inquired directly of the issuing agency.  Guess what?  They’ve always been happy to help.  Point being, there’s no need to go out with bad information or run your mouth when you have doubts.  Of course, this will be of no comfort to the tin-hatters who claim the agencies are in the bag.

Source:
December 2011 Employment Situation
BLS Employment Situation News Release, Friday, January 6, 2012
USDL-12-0012

Part 1: http://youtu.be/ahXIMUkSXX0
Part 2: http://youtu.be/lOIP_Z_-0Hs
How to find the Lucas Angle: http://youtu.be/RRNQAaTVa_A

Click to enlarge:

>

Bloomberg’s Chart of the day (hat tip: Zero Hedge) ostensibly shows a relationship between the US debt ceiling extensions and price of Gold.

Color me unconvinced.

It has a few specific problems. First is the timing: The chart is dated August 1, 2011. Since then, the US credit rating was downgraded, and Gold took a big swan dive. Up 33% YTD at the time of that chart, it finished the year up 10% — certainly respectable, but no where near the home run it was as of August.

The second issue with this chart is that we only see a small slice of history. The correlation may or may not be spurious. We don’t see what took place prior — the pre 1997 era. Prior to this period, there was little correlation between the two. That sort of selective use of a time segment leads to questionable conclusions based upon that one time frame.

I bring this up today because last week, President Obama formally requested the raising of the debt ceiling (again). This is a different debt ceiling structure than the August debacle. Congress now has 15 days from that date to pass a resolution disapproving of this request before the limit is lifted.

David Semmens of Standard Chartered Bank gives us the details why that is unlikely to occur:

“It is important to note that a bill would have to be passed to stop the raising of the debt ceiling this time around – a far more straight forward mechanism that was built into the Budget Control Act of 2011 to ensure a relatively trouble free procedure.

The first hurdle will come in the House of Representatives which returns today (Tuesday 17^th Jan) and is expected to vote on Wednesday (18^th Jan), with the  Republican controlled legislative branch expected to pass a bill of objection which will be sent to the Senate. The Democratic majority Senate resumes after finishing its holiday break next Monday (23^rd Jan) and is expected to reject any move to block the extension, shortly after that. While we would expect that there will be some political posturing surrounding the vote with the House Republicans passing a bill to reject the extension, this would almost certainly be blocked in the Democrat controlled Senate and failing that receive a presidential veto. If the second reading of the bill were to follow a presidential veto, a two thirds majority would be required in both houses to override the presidential veto. A $1.2trn extension will see the debt ceiling raised to 16.394trn and given current projections see the US through until early 2013 before this issue is revisited.

There are plenty of good reasons to own Gold. I remain unconvinced that the debt ceiling is one of them . . .

>

Source:
David Semmens, CFA
Gold vs. Debt Ceiling
Global Research, Europe
Standard Chartered Bank

That is the current time and date, at least the way the Brits configure it (DD/MM/YY)

16.15.14 13.12.11 = 4:15 pm (13 seconds) on the 13th day of the 12 month in the 11th year of the century.

Via Businessweek, we learn that Facebook caused the Greek Debt crisis, Global Warming is caused by NSF R&D budget, and other spurious correlations:

Need to prove something you already believe? Statistics are easy: All you need are two graphs and a leading question.

Wonky amusing fun for any statistically innumerate eejit on your holiday list.

>
click for larger graphic

>
Source:
Correlation or Causation?
Vali Chandrasekaran
BusinessWeek December 1, 2011  
http://www.businessweek.com/magazine/correlation-or-causation-12012011-gfx.html

~~~~~

Jim Mcteague discusses the surprising correlation that Democratic Presidents have had with outperforming economy and stock markets versus Republican Presidents.

He points out that Real GDP growth between 1949 and 2011 was 4.43% under Democratic presidents, while the average growth rate has been 2.43% under Republicans.

As we are so fond of reminding the innumerate masses, however, correlation does not equal causation:

Gripe as you may about President Obama and the economy, he’s been good for stocks. And if history is a guide, he’ll be just as good if re-elected. Dozens of research papers have concluded that the stock market performs noticeably better during Democratic administrations than it does during Republican ones. No one can explain exactly why this is so . . .

Market professionals have multiple theories about a president’s impact on stocks. Asset manager Barry Ritholtz, author of the highly regarded blog “The Big Picture,” says it’s a combination of luck along with a president’s response to economic circumstances.

“That is what separates the great economies from the middling ones. Look at the circumstances that met FDR, Clinton and Reagan,” he says. They all had big challenges, and met them with appropriate responses.

“Ronald Reagan had the luck to come into office in year 14 of a 16-year bear market; he also had as Fed Chief Paul Volcker, who forced a wrenching recession early in his term. But Reagan’s response to those circumstances—significant tax cuts and federal spending followed by gradual tax increases—helped add up to a booming economy,” say Ritholtz.

The whole article is worth a read.

>

Previously:
Presidential Blame & Credit (November 22nd, 2011)

Source:
Democratic Market Magic
JIM MCTAGUE
Barron’s DECEMBER 3, 2011  
http://online.barrons.com/article/SB50001424052748704101304577038140162880680.html

Kevin Slavin argues that we’re living in a world designed for — and increasingly controlled by — algorithms. In this riveting talk from TEDGlobal, he shows how these complex computer programs determine: espionage tactics, stock prices, movie scripts, and architecture. And he warns that we are writing code we can’t understand, with implications we can’t control

Hat tip Flowing Data

Source:
The Unreasonable Beauty of Mathematics
Scientific American
July 26, 2011

Source:
xkcd.com, Cell Phones