Michael Lucas comments on July 1st, painting a bleak picture of Wisconsin employment. For comparison, here are some composite numbers, including the Philadelphia Fed’s coincident index, released today.
Figure 1: Wisconsin Nonfarm Payroll Employment (blue), Philadelphia Fed first benchmark NFP estimate (pink), Citizen Employment (tan), real wages and wages deflated by chained national CPI (sky blue), GDP ( red), coincident index (green) , all in log 2021M11=0. Source: BLS, BEA, Philadelphia Fed [1], [2]and the author’s figures.
The accidental index shows rapid growth in recent months (revises the May number). This is interesting to the extent that the most consistent index is highly dependent on labor market indicators.
The point of Mr. Lucas in his article that reliable employment indicators showed a decline in jobs, namely:
Job losses over the past year can be easily seen by referring to the BLS QCES survey—a loose economic indicator that is among the most accurate and comprehensive market surveys. According to data from that survey, Wisconsin gained a total of 8,099 jobs from 2023Q1-Q3 (Q4 data not yet available). However, in the second and third quarters, Wisconsin lost a total of 20,207 jobs.
He presented this table to support this argument.
Source: Lucas (2024).
Apparently, Mr. Lucas doesn’t know that the QCEW data isn’t seasonally adjusted, so really only q3/q3 calculations make a lot of sense.
Personally, I don’t know QCES (anyone, please tell me what it is). I am familiar with QCEW, which is not a survey, but a census (hence “C” in QCEW).
I organize changes in work from BED (survey), QCEW and CES.
Figure 2: Change from 2021Q4 in Wisconsin nonfarm payrolls from the Current Population Survey (CPS) (blue), the Quarterly Census of Employment and Wages (QCEW) (green), and the Business Employment Dynamics (BED) survey ( tan), all in 000’s. . The QCEW series is seasonally adjusted by the author using X-13 (log transformation) on the monthly data. Source: BLS, and author’s statistics.
To highlight the importance of seasonal adjustment, compare the nsa QCEW vs. of QCEW…
Figure 3: Wisconsin private nonfarm employment from the Current Population Survey (CPS) (blue), from the Quarterly Census of Employment and Wages, not seasonally adjusted (QCEW) (green), from the Quarterly Census of Employment and Wages, (QCEW) (green), all in 000. The QCEW series is seasonally adjusted by the author using X-13 (log transformation) on the monthly data. Source: BLS, and author’s statistics.
Source link