There are three types of people in the world: Those who understand Statistics, and everyone else.

>

Why do so many fund managers underperform? Our host and overlord frequently references cognitive issues, but I am beginning to suspect the problem is simpler: An glaring lack of fundamental math skills.

Those of us who stress data points in our analysis are bumping up against a legion of people — including strategists, commentators and economists — who seem unable to perform simple statistical analysis. Indeed, the willingness to misuse and abuse numbers makes me wonder whether they are polticially motivated. It goes far beyond the “Lies, damned lies, and statistics” to a point that is, to be blunt, embarrassing.

Last month, we watched Zero Hedge and Rick Santelli demonstrate their seeming innumeracy. The Census adjustment is painfully easy to understand, unless you are a) rooting for the end of the world; or 2) a partisan hack.  The combination of armageddon/hackdom sent the “1.2-million-people-dropped-out-of-the-labor-force” story viral.  Of course, that was embarrassingly wrong, but made its way thru the media, including to a White House press briefing. (BTW, have the sources of that misinformation ever posted a correction or retraction? Or are they standing pat with “Duh“?)

The latest innumerate silliness comes to us via an abuse of seasonal adjustment. This time, it is “on a Not Seasonally Adjusted basis, we’ve lost 1.8 million jobs since December!

This story has been floated around in many guises, but I first saw it via the estimable Art Cashin, who channeled The King Report, quoted here at Business Insider (emphasis in original):

Even more disturbing to us was word from a friend who subscribes to The King Report.  He says the newsletter says that without the filter of seasonal adjustment, so far in 2012 nearly 1.8 million jobs have been LOST.  Wow!  We’ll try to check that out.

I submit that this is, in fact, a perfect example of why we have seasonal adjustments in the first place.  People get hired going into the holiday season and are subsequently laid off or quit after the holidays.

By how much? On an Non Seasonally Adjusted (NSA) basis, from August through November 2011, the economy added…wait for it…1.89 million jobs. Retail and Shipping account for the lion’s share of these, with Bar & Restaurants also significant. After the holidays, 95% of these disappear in January and February.  That is why they call these “seasonal jobs.”

But more to the point, let’s take a look at the stunning NSA loss of 1.8 million jobs since December in the context of the previous decade, shall we?  Here’s the February print minus the previous December’s print for the past 10 years:

2003 -2273
2004 -2050
2005 -1880
2006 -1728
2007 -2105
2008 -2519
2009 -3939
2010 -2432
2011 -2037
2012 -1801

Which one of these is not like the others?  To my eyes, it’s the 3.9  million that printed for the similar period in 2009.  But that might tell a different story.  I suspect, perhaps, that this is not about innumeracy, but rather about folks who should know better yet choose to use numbers to mislead and deceive.  It is, frankly, unconscionable.

Folks, this is Statistics 101. There are plenty of things to criticize about various BLS models — this isn’t one of them . . .

Category: Data Analysis, Economy, Employment, Mathematics

Please use the comments to demonstrate your own ignorance, unfamiliarity with empirical data and lack of respect for scientific knowledge. Be sure to create straw men and argue against things I have neither said nor implied. If you could repeat previously discredited memes or steer the conversation into irrelevant, off topic discussions, it would be appreciated. Lastly, kindly forgo all civility in your discourse . . . you are, after all, anonymous.

29 Responses to “Seasonal Adjustments: Fun With Numbers, Redux”

  1. willtruth says:

    BR. Out of curiosity of torturing the data, any thoughts on why the unemployment rate has not seen an uptick as every economist in the world said would happen when the unemployed start job searches again?

  2. CSF says:

    Why don’t we just use year-over-year comparisons? It appears that since December the economy is healthier than the previous year by 236,000 jobs, or a little less than 80,000 per month. Not bad, but not great. We could do the same thing with month-over-month comparisons, trailing yearly comparisons, etc.

    ~~~

    BR: What was done was comparing December one year with February the next. Sheer idiocy!

  3. Greg0658 says:

    I hear ya – our children slaves are not up to the global challenge of providing fresh _ (stuff) to be harvested by the system producers .. come on kids – our future is depending on you’all .. drill baby drill

    http://www.washingtonpost.com/blogs/answer-sheet/post/condi-rice-joel-klein-report-not-the-new-a-nation-at-risk/2012/03/19/gIQAI8hKOS_blog.html

  4. cjcpa says:

    the problem is the rampant cheerleading that goes on in the late fall. Nobody on the teebee ever passes it off as normal, seasonal hiring for jobs that will soon be gone. nothing to see here. Instead it’s full on pom poms.

    The hiring, although seasonal, is given a full court press in the media.

    The loss of jobs to start the year, although typical, is erased with a seasonal adjustment, and all over the teebee is news that we added a million jobs. (except that we didn’t… we just stayed about the same and add in a huge seasonal not-negative equals a positive.)

    The Seasonal Adjustment does not get treated the same way on the way up as it does on the way down. This opens up a ton of room for people to cry foul, which they do.

  5. biscuits says:

    Its not so much the obscure seasonal adjustment that is the problem as the fact that the workforce participation rate gets so little attention. From Daniel Amerman:
    “a detailed look at the government’s own data base shows that about 9 million people without jobs have been removed from the labor force simply by the government defining them as not being in the labor force anymore. Indeed – effectively all of the decreases in unemployment rate percentages since 2009 have come not from new jobs, but through reducing the workforce participation rate so that millions of jobless people are removed from the labor force by definition.”

    He goes on further to dismiss the boomer retirement explanation, showing participation rates have fallen in all categories. For a bit of anecdotal evidence, I can say that those I know who are 50+ are not dropping out of the workforce and instead are planning to in their jobs beyond the age they originally planned to retire because they are afraid of the future of an economy propped up by ZIRP. The cheerleading on unemployment continues to strike me as propaganda, and I ain’t gettin my 411 from ZH or Santelli.

    http://danielamerman.com/articles/2012/WorkC.html

    http://danielamerman.com/articles/2012/WorkC.html

  6. cjcpa says:

    My wife saying:
    “Honey, I usually lose a million dollars at the casino in January, but this year I didn’t so —
    I MADE a million dollars. ”

    You know, isn’t the same as actually making a million dollars. Which would make me really happy.
    Not losing as much as usual, be it dollars, or jobs, in January, does not and should not, have the same effect as REALLY creating a million jobs.

    Ok, I’m done.
    Disclaimer 1 –I made these numbers up. (the actual numbers aren’t the point. )
    Disclaimer 2 — My wife is wonderful and does not gamble.

  7. gordo365 says:

    The average person doesn’t have the math background to understand statistics. Or is that the median person??

  8. JimRino says:

    Both. the average and median person doesn’t have the income to go to good schools, so statistically they don’t make up a large percentage of the college population.

  9. Broken says:

    The “Not Seasonally Adjusted” non-farm payroll is up almost 2 million in January over the prior year January.

    In February, the NSA payroll is up over 2 million over the prior year, very close to the “Seasonally Adjusted” numbers.

    Using the NSA numbers, average monthly payroll growth was 167,000 Jan-to-Jan. Not great, but much better than the last decade average of MINUS 12,000 per month (Jan 2000 – Jan 2010).

    ZH is delusional and Santelli is a shill.

  10. VennData says:

    The stock market is really down 100% not up! It’s inflation that’s running at 100% not the stock market.
    GDP is SHRINKING not growing, Obama has raised taxes by a trillion and will raise them by another trillion!
    Obama took my guns!
    He socialized my family farm! My business! My entire church!
    The world hates us even more!
    We LOST the wars in Afghanistan and Iraq!
    Osama bin laden is still alive!

  11. MayorQuimby says:

    It’s simpler than that – it is mathematically impossible for everyone to overperform! Think about it….

  12. libarbarian says:

    MayorQuimby,

    You have obviously never visited Lake Wobegon

  13. arthurcutten says:

    Absolutely correct.

    The ‘swings’ in the raw number is amazingly broad and very subject to short term influences.

    That is why I always prefer to look at a 9 month moving average of the seasonally adjusted number at the least.

    The first chart in this shows the NSA and SA numbers compared.

    http://jessescrossroadscafe.blogspot.com/2010/09/non-farm-payrolls-devil-is-in.html

  14. DeDude says:

    The problem is that a lot of people start up with a closed mind and already conclusions. To them data is something that should be used to support their conclusions. So if the conclusion they start up with is “Obama is bad” and/or “the Obama economy is bad” then they must misrepresent, misinterpret, or misuse data in such a way that it support their conclusion. Dropping out the seasonal adjustment in that one month where it will turn a big positive number into a huge negative number is a cheap manipulation. Question is have they insisted on dropping out seasonal adjustments for all the months since then? – or do they only report non-adjusted numbers when that gives a more negative impression. It is a lot easier to spot a shill than it is to get an honest answer from them.

  15. biscuits says:

    Does that include Chris Whalen, Reggie Middleton, Robert Brusca, Bruce Krastings, et al, who are contributors on ZH? Or are you just talking out of your ass because you didn’t know it was a compilation website?

    “ZH is delusional”

  16. biscuits says:

    mmkay, so I get that the participation rate was effected by the census adjustment. I am still in agreement that the still large drop is dismissed as reflecting a larger number in the 55+ bracket. Explaining away the drop by assuming its all about retirees is questionable, IMO.

  17. Broken says:

    biscuits:

    Yes, ZH is delusional. Get over it. I still visit the site for the occasional nugget of useful information, but mostly for the laughs.

  18. AHodge says:

    understands statistics > understands seasonals > understands USG Seasonals > understands the ins and outs of the household jobs series expressed in levels.

    they are nearly useless as a time series
    as not rebased, only the ratios, like the unemployment rate, and percentages are worth looking at.

  19. Pantmaker says:

    Barry it isn’t a “glaring lack of fundamental math skills” that causes many fund managers to underperform the market, but rather the mathematical reality of attempting to do so. It’s statistics 101. :)

    ~~~

    BR: 80%? Mathematically, half of everyone is below and above average — so home 4 out of 5 underperform?

  20. AHodge says:

    but it would take the statistically literate to be convinced by your simple display.
    but doesnt stop tens of millions of Obama hating “R’ s fervently grasping “proof” the economy has been ruined. the Rs have periodically been doing this since the late 90s when it works for them.

    its a good quality and intelligence test of those who have embarassed themselves and made themselves stupid with partizan “thinking”

  21. StatArb says:

    Santelli is a partisan buffoon

    .

  22. Winston Munn says:

    In the long run, we are all seasonal adjustments.

  23. Non Sequor says:

    BR: 80%? Mathematically, half of everyone is below and above average — so home 4 out of 5 underperform?

    ~~~

    Half of everyone is under the median. The average may be a different story, depending on the distribution. It may be reasonable to assume that domain specific skills follow something like a power law distribution, with the best performers being 1 to 2 orders of magnitude more “effective” (although the amount may vary depending on how exactly you define “effective”) than the median performer. Fred Brooks, a former IBM manager who wrote extensively on issues in software design, many of which are applicable to other intellectual trades, noted that the best programmers were 5 to 10 times more productive than mediocre ones. It may be that the best managers are much, much more effective at their jobs than the typical manager, making the typical managers look like chumps in comparison.

  24. socaljoe says:

    Why do 80% underperform?

    The probability distribution is not symmetrical… i.e.: 20% outperform by a lot.

    ~~~

    BR: Except thats not true . . .

  25. hdoggy says:

    For those that are better than idiots, but not yet statisticians, the topic today is that the 2008 Nov, Dec, Jan, 2009 Jan, Feb, Mar plunge in numbers exasperated the seasonal adjustments and are still coming back to haunt us. There’s lots of talk on that point, still.

    For those idiots who have become statisticians, global warming and unseasonably warm weather are messing up the adjustments. Still lots of talk.

    For the rest, we’ll just watch seasonality in housing numbers and wait for the next big seasonal adjustments to overshadow employment seasonal adjustments and discuss those in the fall and talk about the how the home buyer credit screwed up the adjustments.

  26. socaljoe says:

    Outperformance is in terms of dollars… could be size of funds and/or % outperformance.

  27. Jim67545 says:

    My favorite quote re statistics: “The only statistics I trust are those I fabricate myself.” Churchill. (Hope I got it right.)
    One of many statistics courses I took spent considerable time on misrepresenting statistics (such as using median vs. average or different time periods to make one’s case) or biasing the perception of statistics and presentations (such as tinkering with the indexes on charts to magnify or diminish apparant changes.) The dark side of statistics. Very interesting and it should be taught widely, if it’s not. So should logic. Most folks are without defenses to all the misleading statistics pervading our environment.

  28. Mark Down says:

    If we would of had that (POSSIBLE) ‘pullback’ everything thing would be rosie!!!!

  29. [...] week’s award goes to New Deal Democrat at The Bonddad Blog and Invictus writing at The Big Picture. The latest employment report error comes via Art Cashin quoting The [...]