Linear Empirical Bayes Prediction of Employment Growth Rates Using the U.S. Current Employment Statistics Survey

P. Lahiri () and Bogong T. Li ()
Additional contact information
P. Lahiri: University of Maryland
Bogong T. Li: U.S. Bureau of Labor Statistics

A chapter in Strategic Management, Decision Theory, and Decision Science, 2021, pp 145-158 from Springer

Abstract: Abstract Many government agencies report monthly estimates of various economic indicators based on business surveys of establishments using traditional design-based methods. Late reporting is a common phenomenon in these surveys and agencies publish revisions of their preliminary estimates as they receive information from late reporters. To maintain public trust, it is important that these revisions are not very different from the preliminary estimates. In the context of the Current Employment Statistics (CES) program of the U.S. Bureau of Labor Statistics, we develop a robust Bayesian two-level model that is useful in reducing the amount of revision of preliminary estimates. The first level of the model develops a relationship between preliminary and final design-based estimates. The second level examines the effects of different labor market factors on final design-based estimates. A linear empirical Bayes prediction (LEBP) method, a robust method based on certain moment assumptions, is proposed to implement the Bayesian model in which the hyperparameters are estimated from the historical data. Using the CES survey data, we show that the LEBP is effective in cutting down the revision substantially and offers a promising alternative to the customary design-based approach.

Keywords: Current Employment Statistics Survey; Multi-level Model; Weighted link relative estimator; Composite estimator (search for similar items in EconPapers)
Date: 2021
References: Add references at CitEc
Citations:

There are no downloads for this item, see the EconPapers FAQ for hints about obtaining it.

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:spr:sprchp:978-981-16-1368-5_10

Ordering information: This item can be ordered from
http://www.springer.com/9789811613685

DOI: 10.1007/978-981-16-1368-5_10

Access Statistics for this chapter

More chapters in Springer Books from Springer
Bibliographic data for series maintained by Sonal Shukla () and Springer Nature Abstracting and Indexing ().