Impact of coronavirus (COVID-19) pandemic on Job Openings and Labor Turnover data for December 2020

The Job Openings and Labor Turnover Survey (JOLTS) national estimates of job openings, hires, and separations have been affected by the coronavirus (COVID-19) pandemic. This page provides further information on the effects of the COVID-19 pandemic for the December 2020 JOLTS news release.

More information on the JOLTS methodology can be found in the JOLTS Handbook of Methods chapter.

Collection mode

Data collection for the JOLTS survey was affected by the COVID-19 pandemic. Prior to the pandemic, JOLTS collected 42 percent of data by phone at the JOLTS data collection center on average. Most phone respondents were asked to report electronically. However, data collection was adversely impacted by the inability to reach some respondents that normally respond by phone. 

Response rates

The preliminary JOLTS response rate for December 2020 was 42 percent. In November, the final response rate was 47 percent. In the year prior to the pandemic, the preliminary response rate averaged 54 percent and the final response rate averaged 58 percent. 

In December, JOLTS response rates declined in all size classes and industries. The industries most impacted were mining and logging; wholesale trade; retail trade; real estate and rental and leasing; accommodation and food services; and federal government. 

Imputation

JOLTS imputation for December resulted in very few cells with more imputation relative to the previous year. The industries which generally experienced more imputation were retail trade; and real estate and rental and leasing. 

Changes to methods

At the onset of the pandemic, the JOLTS program reviewed all estimation and methodological procedures. Changes to the JOLTS estimation and seasonal adjustment methods are described below.

Estimation

For the December preliminary and the November final JOLTS estimates, suppression of the alignment process has been discontinued. The differences between the JOLTS hires minus separations and CES over the month employment changes are no longer significantly different. Please see below for further explanation.

BLS modified the JOLTS estimates for the March preliminary through the November preliminary estimates to better reflect the impact of the COVID-19 pandemic and produce the highest quality JOLTS estimates possible in this unique situation. The estimation process usually includes an alignment of monthly hires minus separations to the over-the-month change in the Current Employment Statistics (CES) employment estimates. BLS suspended the alignment process during this time frame because the differing reference periods for the CES employment estimates (pay period including the 12th of the month) and the JOLTS hires and separations estimates (the entire reference month) led to different measurement outcomes. For example, hires and separations during the latter half of April were not included in the CES employment change for April, but were included in the JOLTS data for the month.

The alignment portion of the JOLTS estimation process was designed to correct a long-term divergence between the JOLTS implied employment change and the CES employment change. JOLTS hires minus separations and CES employment change generally approximate one another. Alignment was developed to correct small monthly discrepancies between the two series that build up over time; it was not designed to address a substantial short-term divergence between the two series.

Seasonal Adjustment

Seasonal adjustment factors can be either multiplicative or additive. A multiplicative seasonal effect is assumed to be proportional to the level of the series. A sudden large increase in the level of the series will be accompanied by a proportionally large seasonal effect. In contrast, an additive seasonal effect is assumed to be unaffected by the level of the series. In times of relative economic stability, the multiplicative option is generally preferred over the additive option. However, in the presence of a large level shift in a time series, multiplicative seasonal adjustment factors can result in systematic over- or under-adjustment of the series; in such cases, additive seasonal adjustment factors are preferred since they tend to more accurately track seasonal fluctuations in the series and have smaller revisions.

In December, the majority of the JOLTS series will retain the additive designation. In accordance with the survey’s usual practice, the seasonal adjustment models and factors will be reviewed at the end of the calendar year, when 5 years of seasonally adjusted estimates will be subject to revision.

Comparison of current month estimates with past monthly JOLTS estimates

Please see the following tables for a comparison of December 2020 estimates to historical levels. 

Last Modified Date: February 9, 2021