For the period March 2020 to September 2021, the establishment survey made two modifications to the birth-death model to better reflect the impact of the COVID-19 pandemic on its employment estimates. These changes included using a portion of business closings (deaths) and openings (births) reported by the establishment survey respondents in the estimation process and adding a regression variable to the model for forecasting net business births and deaths. Effective with data for October 2021, BLS reverted back to the methodology used prior to the onset of the pandemic. For more information about changes to the birth-death model during the COVID-19 pandemic, see the establishment survey's birth-death frequently asked questions.
BLS uses a process to test for the identification of outliers for the purposes of seasonal adjustment. This process did not change after the onset of the pandemic, but BLS did lower the threshold for outlier detection and as a result, identified more outliers than normal for the period of March 2020 to September 2021. As of October 2021, BLS reverted back to the threshold used prior to the pandemic to better adjust for seasonal shifts and as a result, the identification of outliers has returned to pre-pandemic levels.
Last Modified Date: November 5, 2021