The US lost 2.6 million jobs in January:
So how did that become an increase of 353,000 in the official figures? The answer is seasonal adjustments: we always lose millions of jobs after the holiday season, so the numbers are adjusted based on how many we lost vs. how many we expected to lose. This is no simple task, either. Here's a description of the software used to make the calculations:
X-13ARIMA-SEATS is a seasonal adjustment software program developed and maintained at the U.S. Census Bureau.... It offers improvements in diagnostics as well as an enhanced version of the Bank of Spain's SEATS software. The SEATS routines are the result of collaboration with the developers of the software (Agustin Maravall, Former Chief Economist of the Bank of Spain, now retired, and Gianluca Caporello).
Spain! The X-13 software was adopted during Donald Trump's presidency, and is yet another example of the Deep State undermining his goal of America First. Here are the alleged "improvements":
- additional regressors for modeling calendar effects in stock (inventory) time series
- built-in regressors for new outlier types, including seasonal outliers, quadratic ramps, and temporary level shifts
- the ability to designate groups of user-defined holiday regressors and generate model diagnostics for the different groups
- regression model-based F tests for stable seasonal and trading day regressors
- accessible HTML output generated directly by the software rather than by a separate utility.
Very suspicious. No wonder the jobs numbers have looked so good under Biden. You know that Spain is run by socialists, don't you?
Hmmm, F-tests. That must mean it was a failure, of course. At least they are not keeping that part a secret.
But how does it affect my sleep?
Seasonal adjustment also keeps pre-holiday data from showing millions of hires within a couple of months.
Pingback: Hours worked per week fell dramatically in January – Kevin Drum