January Employment Report Preview
Friday's employment situation report is the big statistical release of the week. Billions in market cap will swing on speculative conclusions about preliminary survey data.
The question is so important that we insist on making unwarranted inferences.
This month we have a special treat. We have a timely update on how the BLS is doing with their estimates. If you (unwisely) choose not to think about the problems in the competing methods, then skip to the conclusion for some data you will not see anywhere else.
The Data
We all want to know whether the economy is improving and, if so, by how much. Employment is the key metric since it is fundamental for consumption, corporate profits, tax revenues, deficit reduction, and financial markets.
We would like to know the net addition of jobs in the month of January. This data point is actually a fact, but something that we do not know yet. Eventually we will have this information with a high degree of certainty. It takes about eight months. State employment offices provide data that are used for the benchmarking of the official BLS data. This information is solid, since businesses do not exaggerate employment when it comes to paying taxes.
By the time we have this information, everyone will treat it as "old news." Markets, news sources, and pundits all want to talk about something, and like a spoiled child, they want it RIGHT NOW!
To provide an estimate of monthly job changes the BLS has a complex methodology that includes the following steps:
- An initial report of a survey of establishments. Even if the survey sample was perfect (and we all know that it is not) and the response rate was 100% (which it is not) the sampling error alone for a 90% confidence interval is +/- 100K jobs.
- The report is revised to reflect additional responses over the next two months.
- There is an adjustment to account for job creation — much maligned and misunderstood by nearly everyone.
- The final data are benchmarked against the state employment data every year. This usually shows that the overall process was very good, but it led to major downward adjustments at the time of the recession. More recently, the BLS estimates have been too low.
I think the BLS is honest and does a good job, which seems to put me in a small minority of observers. Despite this support, I question the general concept. The BLS tries to estimate total employment in one month, total employment in another, and subtract the two to determine the difference. When you are talking total payroll employment of over 130 million jobs, even small errors are in the range of 100K jobs or more. Meanwhile, smaller discrepancies from expectations are unwisely viewed as significant.
Competing Estimates
If you accept the idea that the final benchmarking is accurate, then the BLS approach should be viewed as an initial estimate, not the ultimate answer. What we are all looking for is information about job growth. There are several competing sources using different methods and with different answers.
- ADP has actual, real-time data from firms that use their services. The firms are not completely representative of the entire universe, but it is a different and interesting source. ADP sees gains of 170K private jobs. There is a continuing trend of losses in government jobs.
- TrimTabs looks at income tax withholding data. The idea is that this is the best current method for determining real job growth. They see job gains of only 45,000.
- Economic correlations. Most Wall Street economists use a method that employs data from various inputs, sometimes including ADP (which I think is cheating — you should make an independent estimate). I use the four-week moving average of initial claims, the ISM manufacturing index, and the University of Michigan sentiment index. I do this to embrace both job creation (running at over 2.5 million jobs per month) and job destruction (running at about 2.3 million jobs per month). In mid-year the sentiment index started reflecting gas prices and the debt ceiling debate rather than broader concerns. When you know there is a problem with an input variable, you need to review the model. For the moment, the Jeff model is on the sidelines.
The problem with all of these methods is the scoring system. Everyone foolishly takes the BLS estimate as "official" even if the other approaches eventually turn out to be more accurate. Let us look more closely at this question.
The Final Verdict
As noted in the introduction, we eventually have actual hard data from state employment agencies. This is reported via the business dynamics series, which was updated today. Eventually the big-time pundits will pay some attention to this, but for now I am virtually alone in citing these data. Here is a crucial chart:
The last column shows the error from the current BLS estimate and the final data. I am working on sharpening this up, since it is using not the original BLS estimates, but the revised version. The interpretation is that the BLS was too optimistic for the quarter ending in March — something that I noted as a concern a few months ago. We now know that they were too pessimistic for the quarter ending in June.
I believe that TrimTabs, ADP, NewArc, and other forecasters actually do as well as the BLS in the preliminary estimates. This means that the market should embrace various estimates.
It is also clear that the knee-jerk criticism of the BLS and the job creation estimation process is completely wrong. The BLS has been pretty accurate over the last year, and is actually under-estimating new job creation.
New jobs are created at a pace of nearly 7 million per quarter. If you do not know this, you don't know Jack about employment. I am still waiting to hear this information on CNBC's Friday morning report.
The way the BLS estimates jobs reminds me of how my friend proposed to determine the weight of an elephant hair. Weigh the elephant, shave off the hair, and reweigh the elephant 🙂
Glad you mentioned the 7 million new jobs. People don’t realize that unemployment would be multiples of what we have now, if it weren’t for significant (but still inadequate) levels of job creation.
Aaaa – I don’t think 7 million jobs are “created” every quarter; they ARE made available to new employees, but for the most part they are openings due to someone leaving the job rather than requiring more workers.
“Created” is usually interpreted as new or additional and that just isn’t the case.
J.Wiedwald — You are mistaken. The methodology is clearly stated in the BLS technical bulletins. BTW, about 1.2 million jobs are created every quarter at new establishments.
Here is a quote from their tech notes: “Gross job gains include the sum of all
jobs added at either opening or expanding units. Gross job losses include
the sum of all jobs lost in either closing or contracting units. The net
change in employment is the difference between gross job gains and gross
job losses.”
Proteus — That is a good analogy. This also helps people understand how we can have initial claims running at 375K per month and still have reduced unemployment.
Thanks for joining in.
Jeff
Hi Jeff! I just came across your blog today, and I’m glad to see someone I can agree with writing about employment numbers. I’m not an economist or a statistician; but I’m very interested in jobs numbers and calculations thereof. I started investigating jobs numbers back when the economy started to crash in late 2008. I needed to understand what these statistics meant. I have found and read so much that is just plain wrong, so I value your thoughts.
I also agree that, considering the size of the population and the number of jobs, the BLS does a very decent job in its estimates and is fundamentally honest. I wrote early last year, “If the BLS is “cooking the books”, why didn’t they cook the unemployment rate down below 8.5% or even 8.0% before the November 2010 midterms?”
And many, many people forget that, even though many people are laid off monthly, many people are also hired monthly, in good times and bad. Now, how do the numbers reported in business dynamic tie into the reports of JOLTS numbers of new hires vs. layoffs/quits? There were about 11,400,000 private hires in that same three month period (March through June 2011) and 11,059,000 private separations, for an increase of 341,000 hires over separations for that quarter. That underestimates both the private CES numbers and the business dynamic numbers.. though it is really close to the CES estimates for the same period of time. It also shows how much “churn” there is in hiring and separating during any month.
Molly — Thanks for joining in. All good points. There is some variation in the nature of the surveys and the timing of the various BLS approaches, but they are all close.
You have the key point: The key aspects of business dynamics.
Jeff
It was the most flawed and misleading BLS report in decades.
December to January BLS reported U3 headlines were completely misleading – BLS dumped 10 years worth of US population/demographic revisions into a single month and used it as the baseline aggregate number for computing reported U3.
Joe — You are mistaken. The problem lies not with the BLS, but with the Census Bureau. They estimate population changes each year. When the decennial census is available, they have improved numbers.
What the BLS does is implement the improved census data. Do you think they should ignore this? They then have a choice of revising all of the estimates for the last ten years to smooth out the population effect, or making a one-time adjustment. If you read their report — right down to the bottom of the page — you will see that this is explained very carefully. The census change had zero effect on the unemployment rate in U3. There was an improvement and also improvement in labor force participation.
You need better sources for your information!
Jeff
Re: “There was an improvement and also improvement in labor force participation.”
Jeff – you are mistaken big time. The monthly employment number is just an estimate by BLS economists
BLS reported their guesstimates based on assumptions (models) and inflated above previous years average seasonal adjustments – these were the estimates based on opinions of BLS economists, not the actual real numbers.
The economy lost 2,689,000 jobs, but the seasonal adjustment was 2,932,000 jobs. How did they come up with this above average seasonal adjustment number – 2,932,000? Why don’t they (BLS) show us how they derived this seasonal adjustment number and why they think the seasonal adjustment should be higher this year vs. prior years?
People who claim “there was an improvement” are having a hidden agenda or simply lying. Nobody can make such claims (not even BLS economists) because these estimates and assumptions are subject to large revisions in the following months.
Joe — The seasonal adjustments are not guesstimates, as you call them. It is a sophisticated statistical process developed over a number of years with a lot of constructive criticism involved. It is a very open process which you can learn about here: http://www.google.com/url?q=http://www.bls.gov/ces/cessa_oview.pdf&sa=U&ei=jtQuT8vRDcGgtwf6k_HdDw&ved=0CBYQFjAJ&client=internal-uds-cse&usg=AFQjCNGgvIsoUXmiig4vb5Wev70J52X1JQ
If you just went to bls.gov and searched for seasonal adjustments you would find many pages of discussion and description as well as past data. You could look at past years and compare the year-over-year changes to see that the result is the same.
Or you can start with your conclusion and stick with it, regardless of the evidence. As I said, you need to find some new sources!