This page has been archived and commenting is disabled.
Mystery Of July Retail Sales "Beat" Solved: It Is All In The "Seasonal Adjustment"
The July retail sales beat came as a surprise to many: an 0.8% increase (full series here) at a time when the data was supposed to grow at less than half this would surely be indicative of a potential turnaround in the US economy. Then we decided to do a quick spot check if maybe the Census Bureau had not adopted one of the BLS' worst habits: fudging seasonal adjustment factors. The reason for this is because we happened to notice that Not Seasonally Adjusted (full series here) retail sales data in July actually declined by 0.9% from $405.8 to $402 billion. Of course, if the Census Bureau was using a consistent, or at least remotely comparable July seasonal adjustment factor as it has in the past, this would make sense and we would move on. So we decided to look at what the July seasonal adjustment variance over the past decade has been. What we found would have shocked us if indeed this is not precisely what we expected: with the July seasonal adjustment factor routinely subtracting a substantial amount from the NSA number, averaging at -$5.2 billion, in 2012, for the first time this decade, the seasonal adjustment not only did not subtract, but in fact added "value" to the NSA number, resulting in a seasonally adjusted number that was $1.9 billion higher than the NSA number at $403.9 billion.
So what would have happened if instead of arbitrarily deciding to add a seasonal contribution for the first time in a decade, the Census Bureau had used the last decade average factor of $5.2 billion (not adjusted for inflation, so the end number would be far greater)? Instead of rising by 0.8% Seasonally Adjusted retail sales would have declined from $400.7 billion to $395.5 billion, or a 1.3% decline.
And that is how data is fudged.
Those curious what the model behind this now glaringly obvious seasonal adjustment fudge is, read on (source):
We use the X-12 ARIMA program to derive the factors for adjusting data for seasonal variations and, in the case of sales, for trading-day and holiday differences.
Adjustment of estimates is an approximation based on current and past experiences. Therefore the adjustments could become less precise if current competitive pressures, changes in consumer buying patterns during holiday periods, and other elements introduce significant changes in seasonal, trading-day and holiday patterns.
Each month for sales, concurrent seasonal adjustment uses all available unadjusted estimates (including the latest preliminary and advance estimates) as input to the X-12 ARIMA program. Factors derived from concurrent seasonal adjustment for sales are applied to the unadjusted advance, (one month after the preliminary) preliminary, and final (one month before the preliminary) estimates and to the previous year estimates that correspond to the advance and preliminary months.
The table Combined Seasonal, Trading-Day, and Holiday Adjustment Factors for Retail and Food Services Sales by Kinds of Business presents the combined seasonal, trading-day, and holiday adjustment factors that are used to adjust sales estimates. For kinds of business whose last observation is an advance estimate, two months of projected factors are shown. For all other kinds of business, three months of projected factors are shown. Projected factors are estimates of the factors that will be used to derive adjusted estimates when unadjusted estimates become available.
More information about the X-12 ARIMA Program is available on the Census web site at http://www.census.gov/srd/www/x12a/ .
»
- 16830 reads
- Printer-friendly version
- Send to friend
- advertisements -
must... reelect... obama...
Lies, damn lies, and statistics. All the stops are pulled out.
so this means QE is still coming? See how well their baffle strategy works! Gotta give ZH credit for doing in a few minutes what used to take the general investing public (or what's left of them) and the algo's days to interpret.
Great piece of research. Thanks ZH.
'Seasonal adjustments' tweaked as necessary. What a crock of shit these data are.
Now can everyone just wake the fuck up!
If it is a Number from the Government, do not trust it.
If it is a Number from a Publicly-traded company, do not trust it.
If it is a Number from a Market in which the Fed is active, do not trust it.
If it is a Number to settle International Trade, do not trust it.
If it is a Number quoted by any Politician, do not trust it.
If it is a Number quoted by any Economist, do not trust it.
Can I ADD...
Do not Beleive the GOLD Prices Quoted. Be happy you are owning a REAL ASSET, Probably
worth North of 25K were it not for the bogus manipulations...
Be happy you can actually still buy GOLD at these prices today... Tomorrow - ???
"I, for one, welcome our new number-fudging overlords!"
Numbers are all bullshit nowadays man ... nothing but goddamn fucking bullshit
The hidden moral to this story is if you are the programmer in charge of developing a seasonal adjustment algorithm don't open up the Email from someone named 'Lolita' inviting you to see her pics. After that your program will adjust things just the way your handlers want them to be adjusted.
"the International Monetary Fund forecasts the slowest trade growth in three years."
http://tiny.cc/odc1iw
I recommend in the future that all numbers issued by the government have an "i" attached (though ZH readers have likely assumed they are imaginary already):
For example: 4 becomes 4i (that way people will know that its an imaginary number (on the y axis of the complex plane)
Another specific example: The BLS reported today that GDP was 1.5i %, while retail sales grew at 0.8i %.
Yeah Tyler is most definately on it.
Most informative site available for those that want the truth...
This is precisely why this site is my first and foremost resource to fact check the eyebrow raising "stats" and data coming out these days. Also, zerohedge got a Santelli shoutout for this piece today. I guess you guys are sort of a big deal
This is precisely why this site is my first and foremost resource to fact check the eyebrow raising "stats" and data coming out these days. Also, zerohedge got a Santelli shoutout for this piece today. I guess you guys are sort of a big deal
Seasonal Adjusment equals extrapolating shit.
And shit is what you get from the manipulated data and from the administration
Could explain why the GDP figures are a bit more accurate with retail sales, but then GDP is fudged with all that inflation expectation stuff...
but, but ...
this time it's different.
It's the secret sauce that makes all statistics taste just right!
So......who do I call to "seasonally adjust" my checking account? I could use a few grand right now.
I'm shocked. Data fudged...tell me it ain't so.
Good to see Spain is getting on top of the housing crisis with another inspired policy move.
"Spanish new home VAT increases to 10%: The Spanish government has confirmed that value added tax on new homes will rise to 10% of purchase price next year, from 4%, according to PIE Magazine. Since it has already raised VAT on refurbishments to 21% from 8%, and abolished mortgage tax relief, the move adds to problems in clearing the 800,000 vacant housing overhang."
its not a tax silly....it is a fee....they should change it to VAF
The Spanish government could save themselves a lot of time enacting new legislation by simply enacting: "We are the Government give us All your Money!"
jeezustapdancingchrist. can we knock it off with seasonal adjustments already and just get a report of the raw numbers? i hate this shit
Ummm...no...we cannot do that as it would not shine a good light on the current desperate, failing status quo morons in charge of destroying the US economy for the last 25 years. And so we must fudge and pretend...so that folks don't get restless and quit watching...ummm...errrr...I don't even know what anyone is watching these days...ah, forget it.
Without the Ministry of Fudging, the raw stats might cause the muppets to stampede.
A greenie for 'jeezustapdancingchrist'
garbage in garbage out....literally
This is bullish; an ACTUAL decrease in retail sales means QE is on! Stupid algos they're missing an excuse to rally the market!
IT is the new math: 2+2= what ever you would like it to be.
The Übermensch makes his own reality.
Obama: The Economy is recovering, we got retail sales up .8% I dont even now what that is but its going up so it must be good
Goin' up.
Politicians don't say "ing."
Wouldn't it have been a lot easier to say:
"We pulled this number out of our collective asses this year due to our bosses burning desire to be re-elected."
I think I would be more inclined to the believe the figures if the Census Bureau announced that Martians had landed and were doing shopping.
Baaa baaa baaa
--we the sheeple
seasonal seasonings by emeril
In today's market, investor will only dump stocks in good news! today market should sell off
Banana republic USA
Banana world, buddy.
"Fudge Factor"
Hashish in the Brownies
Grain alcohol in the Punch Bowl
"Oh, someone didn't tell you? Well? Do you feel good?"
And again, no QE until after the election. Smoke and mirrors until then. Wonder when Mr. Market will figure this out?
Mr. Market won't......thats the genius of the BS
Mr. Market passed on some time ago.
He has been replaced by some rich kids toy.
how many "NSA"s do we have?
this one is right up there prop-wiZe: "adding value"
dey lucky dey ain't gettin taxed for that malarky!
The Fed puts out this number...basically, guys you need to sell off your shit so we can do QE.
...the season is the reason...wait 'til they tell how to recalculate the height of the fiscal cliff during descent...
More artificial sweetener in the fudge…
The Retail Sales report and manufacturing statistics are simply measurements of inflation, not of actual production. Instead of measuring units of production, these reports all first measure the flow of sales measured in dollars.
Retail Sales “measures sales in dollars and since inflation is incorrectly measured is not adjusted appropriately. Since inflation is way understated, it overstates Retail Sales. Another flaw in this report is substitution bias, that is it only measures stores that are open over the last year and fails to account for stores that have closed…truth and transparency are not high on the list of those who control economic statistics.” (Nathan’s Economic Edge)
Disposable income is flat, construction spending bottom bouncing, credit growth remains all in student loans, July unemployment 22.9% (Shadowstats)…
un...fucking...real.
This country is one big manipulated pile of corporate run horseshit.
Tired of the FED print and push stock market methods....... others are starting to see it too
http://finance.yahoo.com/news/chinese-companies-pull-us-stock-095649722....
Even if we put the fudged number aside. It's retail, not production. Meaning if retail should go up, that is nothing more than debt spending. There is no recovery.
No volume. Market to sell off.
Bots bracketing a trading range while smart investors stay away from the insanity of this broken thing that is supposed to be a market, but isn't any more.
These pathetic volumes do hurt the big Wall Street banks, so it would be poetic justice if this continued for a while longer.
Thanks for the analysis ZH.
this is CRAZY...i'm buying more US treasuries
http://govttrader.blogspot.com/
Do you get an employee discount?
Well, pretty soon, they are going to "seasonally adjust" volume traded in stock market.
Cunning plan, Baldrick.
Not only are all the markets manipulated - stocks, bonds and commodities, but also all the data. Who would be crazy enough to try to trade under these conditions? You will lose everything to the HFT algos which can react in microseconds, not to mention the insiders who know what is coming next.
This makes more sense and is what I see 'on the ground."
...and in other bullsih news (esp for NYC real estate):
Chinese companies pull out of US stock marketshttp://finance.yahoo.com/news/chinese-companies-pull-us-stock-095649722....
I guess all those "aliens' buying up property will now be selling and moving to where the action is...HK and Shanghai, Frankfurt and London. NYC is so old hat.
Score one more for Dearest Leader and Klack. You ain't seen nothing yet. Just you wait and see all the limosene libtards, lap dogs, and other useful idiots, you will be up against the wall and handled like the tools you are. Pop goes the weasel! Sweet dreams...
So, I looked up the NON adjusted numbers:
June 2011: 392,888
July 2011: 388,749 Million.
June 2012: 405,820
July 2012: 401,988
Looking back, historically the only months with values exceeding 400K are in December(Chirstmas).
I haven't perused the various categories. I know that food and gas prices have soared over the last 5 years, and my gut tells me that "retail" sales are going up b/c the economy is booming. Instead, people are spending a lot more for essentials (food, gas, heating oil and clothes.)
ZH: give me a chart overlaying "Retail" sales with essential spending and discretionary spending.
It’s the SNAP folks in my coastal area who appear to have the discretionary income left over for mall-type dining out and cheap entertainment, having all their nondiscretionaries paid for by the government’s transfer of wealth program; the retirees seem to have disappeared from the public streets…it’s their money, their savings, Bernanke is spending into the economy, only they aren’t the ones “entitled” to spend it. Therefore, the indirect $78 billion boost in “consumer spending…”
“From 2007-2011 spending on the Supplemental Nutrition Assistance Program (the SNAP program, informally known as the food stamp program) increased 135 percent to reach a cost of $78 billion last year (2011) alone, the report reveals.”
As ZH blogger MrBoompi 6/22/2011 put it: “Until they remove government spending and ‘banking contributions’ from GDP calculations they're not worth the paper they're printed on anyway. These ‘organizations’ suck money from the ever-shrinking productive part of the economy.”
Read more: http://dailycaller.com/2012/04/20/cbo-cost-of-food-stamp-program-increased-135-percent-over-last-4-years/#ixzz23WxMAskv
Tyler, I get the move is a Corn Syrup Statistic designed to move opinion. But why/ Would not a horrible number serve TPTB better?
In today's fucked up market bad news is good because bad news means greater chance of QE. I am not sure why we have associated government printing with market positive (nominally, sure but in the end you are Zimbabwe) but the 'market' does.
If bad news is good, then good news is bad ( or at least not as good), which gives the Fed some room to print, not to mention some element of surprise as 'investors' have priced in QE already.
In short the Fed needs a selloff, but none of the insiders will take the hit, so they are trying to fool the last few retail people left in the 'market' and get them to dump... on good news.
Just another example of how sick and twisted our financial system has become while under the control of these sociopathic terrorists we call bankers and politicians.
There are no more rules anymore except saving the world which is Job #1. ANYTHING that could possibly send the stock er confidence market down is not allowed anymore. Anything that would crash Europe is not allowed anymore. ESM doesn't have a banking license? We can find a way around that...just route funds through Zambia, back to New Zealand into the Caymans and back to the Bank of Greece...unbelievable.
Not saving the world, trying to save the status quo is what is going on here, but the skimmers are going to fuck it up just like everything they touch, and once they crap the bed things will get better until it eventually starts over again (unless we man up and make some fundamental changes for the better). We already have a clear example of them trying to lay blame for their ways at the feet of the little guy from peregrine.
The world is the status-quo - to them.
What's good for Apple is good for America.
Dup
Just like last weeks jobs report, gold has had a rethink and is turning around. Fool me once...
Edit: Looks like equity markets (i.e. HFT bots) have come to the same realization.
The seasonal adjustment model has been developed jointly with Bank of Spain - I kid you not. See last entry in this glossary:
http://www.census.gov/srd/www/x12a/glossary.html
Nice catch, let out an audible "holy crap", which is notable due to my lack o' surprise at most of this shit.
The Let Them Eat Cake bureau? On the ground reality is deteriorating faster than it ever has, yet the government and its propoganda arm of Wall Street is trying to make it look like times are better than ever.
Zero prosecutions for financial fraud will do that.
I've heard of new math, but this is ridiculous.
Now we have Nuage Maths !
This is telling as to why all the countries in the world are slowly turn againt our currency. Everything we read is a lie or manipulated.
USA: The Goldman Sachs of nations.
C'mon - its just a slightly adjusted number...
Just like the seasnally adjusted happiness number. Sure, your home is repossesed, your divorced now, your children are in cults, your unemployment has run out, your eating from dumpsters, and your living in an abandoned refrigerator, your health insurance has lapsed, so your treating your kidney dialysis yourself by running your blood through discarded coffee filters....BUT, SEASONALLY ADJUSTED, YOU HAVE NEVER BEEN HAPPIER!!!
See?
@Tyler: Two points. First, it appears that there are additional corrections to the SA figures beyond the 'adjustment factors' you have linked to - a simple spreadsheet will show that there are consistently large "errors" between the reported SA figures and the 'expected' based upon NA/Adj Factor.
Second, why are we even going crazy on a time series which admits to an error bar of 0.8%? In most months this is larger than the reported change, ie the actual is just noise.
Using econometric stuff just to multiply negative numbers. . of course: "- x - = +"
I love how those on the street get excited over this "beat". "It's a whole 0.03%!!!!111 ZOMG time to buy stocks!!1111"
What a lot of fucking suckers.
So Santelli does exactly what WE all do when a number comes out. We watch the boob-tube, think about how the number is full of shit, and then check out ZH to see what is really going on.
Nice Santelli plug - "'Tis the seasonal, as ZeroHedge points out [...] go check it out for yourselves".
i didn't know baghdad bob could do statistics.
There are lies, damn lies and Bureau of Labor Statistics. Guess which one the US Government went with.
Makes me think about the old wild west potion salesman selling from the back of a wagon. He decided to try to sell some rabbit pellets (aka rabbit shit) as "smart pills".
One day a customer came back & said "hey man, these pills taste just like rabbit shit". The old potion guy replied, "see they're working --- you're getting smart"
Hey . . . we're trying to win an election here!
who changes their vote basis on one month's retail sales numbers?
Just a minor correction, although the overall pooint still holds. SA is multiplicative, not additive. The average SA factor for July from 1992 through 2011 was 0.98796958. This month's was 1.004829. Using the average on this month's raw numbers gives a drop of 0.9% in Retail Sales.
do not seasonal adjustments under the X-12 ARIMA Program go back 5 years, with greater weighting for the most recent? so what did we lose in 07, how do 2010 & 2011 compare...
Not surprising. I can't trust my old Ma' anymore neither.