BLS Business Surveys in the Wake of COVID-19: Changes to Data Collection, Imputation, and Estimation

• Activity Number: 147 - Producing Official Statistics During a Pandemic: Advances Under Adversity
• Type: Invited
• Date/Time: Tuesday, August 10, 2021 : 10:00 AM to 11:50 AM
• Sponsor: Government Statistics Section
• Author(s): Kenneth W Robertson*
• Companies: U.S. Bureau of Labor Statistics
• Keywords: COVID-19; BLS; estimation; imputation; data collection; business

Abstract

The US economy lost a staggering 22 million jobs in March and April of 2020 following the slowdown and shutdown of much of the usual face-to-face business activity as COVID-19 cases rapidly spread. This extraordinary employment decline coincided with evolving rules for social distancing to fight the spread of the novel coronavirus, a substantial increase in continuous work-from-home, and rapid efforts by the Congress and the Federal Reserve Board to provide fiscal support to taxpayers and businesses to reduce the impact of job losses on the economy. As these social and fiscal changes occurred, BLS was faced with huge challenges in data collection, and in the estimation and imputation of massive employment changes. This paper describes the major challenges and the changes made in data collection, estimation, and imputation, and provides an analysis of the success of these rapidly implemented procedure changes. The challenges and changes described are focused on three business surveys: the Current Employment Statistics survey, the Job Openings and Labor Turnover Survey, and the Quarterly Census of Employment and Wages.