Changes to the Net Birth-Death Model Due to the COVID-19 Pandemic

The labor market experienced widespread disruption at the onset of the pandemic, leading to a breakdown in the historical relationship between business openings (births) and closings (deaths). To better reflect the net effect of the contribution of business births and deaths to the estimates during the pandemic, BLS implemented special procedures to the net birth-death model in March 2020. Effective with the release of October 2021 preliminary estimates, BLS determined that adjustments to its birth-death methodology were no longer necessary. Therefore, the birth-death contribution to establishment survey estimates beginning with October 2021 are forecast using the methodology used prior to the onset of the of the COVID-19 pandemic (described on this page). More information about changes to the CES net birth-death model during months affected by the COVID-19 pandemic are available on our birth-death frequently asked questions page at www.bls.gov/web/empsit/cesbdqa.htm#qa8. Any month in which adjustments were made to account for pandemic affects is footnoted in the tables below.

CES Net Birth-Death Model

Currently, the CES sample includes about 131,000 businesses and government agencies drawn from a sampling frame of Unemployment Insurance tax accounts which cover approximately 670,000 individual worksites. The active CES sample includes approximately one-third of all nonfarm payroll workers. The sample-based estimates are adjusted each month by a statistical model designed to reduce a primary source of non-sampling error which is the inability of the sample to capture, on a timely basis, employment growth generated by new business formations.

There is an unavoidable lag between an establishment opening for business and its appearance on the sample frame making it available for sampling. Because new firm births generate a portion of employment growth each month, non-sampling methods must be used to estimate this growth.

Earlier research indicated that while both the business birth and death portions of total employment are generally significant, the net contribution is relatively small and stable. To account for this net birth-death portion of total employment, BLS uses an estimation procedure with two components: the first component excludes employment losses due to business deaths from sample-based estimation in order to offset the missing employment gains from business births. This is incorporated into the sample-based estimate procedure by simply not reflecting sample units going out of business, but imputing to them the same trend as the other firms in the sample. This step accounts for most of the birth and death employment.

The second component is an auto-regressive integrated moving average (ARIMA) time series model designed to estimate the residual birth-death employment not accounted for by the imputation. The historical time series used to create and test the ARIMA model was derived from the UI universe micro level database, and reflects the actual residual of births and deaths over the past 5 years. This ARIMA model was originally applied once a year using new data to calculate the net birth-death forecasts. Effective with the release of preliminary January 2011 employment estimates in February 2011, BLS began updating the Current Employment Statistics (CES) net birth-death model component of the estimation process more frequently, generating birth-death forecasts on a quarterly basis instead of annually. For more information about the quarterly birth-death forecasts, please see www.bls.gov/ces/methods/ces-quarterly-birthdeath.htm. For a comparison of annual birth-death forecasts to quarterly birth-death forecasts for all years from 2004 to the 2014 benchmark, please see www.bls.gov/ces/methods/quarterly-birth-death-comparison.htm.

The net birth-death model components are unique to each month and exhibit a seasonal pattern that can result in negative adjustments in some months. These models do not attempt to correct for any other potential error sources in the CES estimates such as sampling error or design limitations. Note that the net birth-death forecasts are not seasonally adjusted, and are applied to the not seasonally adjusted monthly employment estimates to derive the final CES employment estimates.

The table below shows the net birth-death model adjustment used in the published CES estimates since the establishment of the most recent benchmark level for March 2021.

2021 Net Birth-Death Forecasts, not seasonally adjusted (in thousands)
CES Industry Code	Supersector	Apr⁽¹⁾ ⁽²⁾	May⁽¹⁾ ⁽²⁾	Jun⁽¹⁾ ⁽²⁾	Jul⁽¹⁾ ⁽²⁾	Aug⁽¹⁾ ⁽²⁾	Sep⁽¹⁾ ⁽²⁾	Oct⁽²⁾	Nov⁽²⁾	Dec⁽²⁾
10-000000	Mining and logging	0	2	1	1	0	0	1	0	0
20-000000	Construction	30	31	23	16	19	4	27	-9	-17
30-000000	Manufacturing	1	10	3	2	7	1	9	4	1
40-000000	Trade, transportation, and utilities	21	33	19	23	19	10	51	17	8
41-420000	Wholesale trade	4	7	1	2	3	-4	14	2	0
42-000000	Retail trade	9	15	8	13	6	5	19	0	-1
43-000000	Transportation and warehousing	8	11	10	8	10	9	18	15	9
44-220000	Utilities	0	0	0	0	0	0	0	0	0
50-000000	Information	5	5	-1	7	3	0	11	3	1
55-000000	Financial activities	13	10	0	10	4	-8	32	1	7
60-000000	Professional and business services	97	26	-15	75	48	-20	135	9	-19
65-000000	Education and health services	40	20	-29	41	18	-13	76	14	-14
70-000000	Leisure and hospitality	88	93	95	84	20	-56	17	-22	-3
80-000000	Other services	14	9	10	5	8	-5	20	0	-6
00-000000	Total nonfarm net birth-death forecast	309	239	106	264	146	-87	379	17	-42

2021 Total nonfarm over-the-month change, not seasonally adjusted (in thousands)
	Jan	Feb	Mar	Apr	May	Jun	Jul	Aug	Sep	Oct	Nov	Dec
Total nonfarm over-the-month change				1,050	946	1,189	-41	495	704	1,659	900	142

2022 Net Birth-Death Forecasts, not seasonally adjusted (in thousands)
CES Industry Code	Supersector	Jan	Feb	Mar	Apr	May	Jun	Jul	Aug	Sep
10-000000	Mining and logging	-1	0	0	-1	1	0	0	0	0
20-000000	Construction	-43	12	19	35	36	21	16	11	-2
30-000000	Manufacturing	-9	7	2	0	9	5	2	5	-1
40-000000	Trade, transportation, and utilities	-19	21	6	11	20	5	30	18	-3
41-420000	Wholesale trade	-10	5	-2	-1	3	-4	5	2	-7
42-000000	Retail trade	-7	13	5	8	11	6	15	8	1
43-000000	Transportation and warehousing	-2	3	3	4	6	3	10	8	3
44-220000	Utilities	0	0	0	0	0	0	0	0	0
50-000000	Information	-7	5	2	5	5	0	8	4	-1
55-000000	Financial activities	-25	11	-2	9	6	-6	16	3	-17
60-000000	Professional and business services	-30	35	-19	113	24	-16	76	23	-46
65-000000	Education and health services	23	20	-22	44	15	-27	55	17	-31
70-000000	Leisure and hospitality	0	37	35	108	88	81	99	22	-63
80-000000	Other services	-3	8	2	16	9	1	7	6	-8
00-000000	Total nonfarm net birth-death forecast	-114	156	23	340	213	64	309	109	-172

2022 Total nonfarm over-the-month change, not seasonally adjusted (in thousands)
	Jan	Feb	Mar	Apr	May	Jun	Jul	Aug	Sep	Oct	Nov	Dec
Total nonfarm over-the-month change	-2,847	1,638	762	1,052	771	879	-349	384 ^(p)	431 ^(p)
Footnotes ^(p) Preliminary ⁽¹⁾ Net birth-death forecasts for this month use major industry sector sample link regressors in addition to the historical net birth-death input data in the RegARIMA forecasts. These are included to account for rapid changes in employment due to the COVID-19 pandemic. ⁽²⁾ CES sample enrollment for this month is lagged by one quarter (for more on this see the CES notice). Therefore, net birth-death forecasts have been lagged to match that sample. For more about sample rotation see the Birth-death model under quarterly sample rotation in the CES Technical Notes.

Additional information on the CES birth-death model is available in the CES Technical Notes under Business birth and death estimation (www.bls.gov/web/empsit/cestn.htm#section6c) as well as on the birth-death frequently asked questions page at www.bls.gov/web/empsit/cesbdqa.htm.

Historical birth-death forecasts are available at www.bls.gov/web/empsit/cesbdhst.htm.

An overview of the CES birth-death model, including a detailed description of the original methodology is available at www.bls.gov/opub/mlr/2006/05/art4full.pdf.

Last Modified Date: October 7, 2022