Economic research is a critical function at the Bureau of Economic Analysis, and is conducted by staff in each of the program offices as well as the Office of the Chief Economist. BEA researchers produce a wide variety of articles, papers, and working papers, as well as regularly participate at professional meetings around the world. BEA researchers also produce a wide variety of methodological and statistical reports to support the continued improvement of the U.S. System of National Accounts.

Within BEA, a substantial number of researchers are actively involved in research on a full slate of issues of interest to the Bureau. BEA encourages these researchers to engage in independent research related to BEA statistics and their uses and supports publication of their work in professional journals and other academic venues.

BEA also supports research by academics on these issues through the Special Sworn Employee program, by making data available, by supporting National Science Foundation (NSF) proposals that deal with issues of interest to us, and by supporting a fellowship program with the American Statistical Association and National Science Foundation.

Latest Research

The views expressed in these papers are solely those of the authors and not necessarily those of the U.S. Bureau of Economic Analysis or the U.S. Department of Commerce.

Predictive Testing for Granger Causality via Posterior Simulation and Cross Validation

This paper develops a predictive approach to Granger causality testing that utilizes k-fold cross-validation and posterior simulation to perform out-of-sample testing. A Monte Carlo study indicates that the cross-validation predictive procedure has improved power in comparison to previously… Read more

By Gary Cornwall, Jeffrey A. Mills, Beau A. Sauley, Huibin Weng

Implications of Geometric Cohort Depreciation for Service-Life Distributions

This paper decomposes cohort-level Geometric depreciation into a weighted average of individual non-Geometric forms. The individual forms are general enough to represent actual individual depreciation patterns adequately, and the weights on individuals resemble Gamma service-life densities under… Read more
By Brian Sliker

Improving the Analysis of Randomized Controlled Trials: a Posterior Simulation Approach

The randomized controlled trial (RCT) is the standard for establishing efficacy and tolerability of treatments. However, the statistical evaluation of treatment effects in RCTs has remained largely unchanged for several decades. A new approach to Bayesian hypothesis testing for RCTs that… Read more

By Jeffrey A. Mills, Gary Cornwall, Beau A. Sauley, Jeffrey R. Strawn

Aggregate Effects and Measuring Regional Dynamics

Empirical models of regional adjustment often control for aggregate effects when estimating the impact of regional shocks. It is, however, difficult to filter out the effects of aggregate shocks— such as national recessions— because the incidence of these shocks varies across space and time. We… Read more
By Ryan Greenaway-McGrevy, Kyle K. Hood