Simultaneous Reconciliation of Large Disaggregated Time Series of U.S. Input-Output Accounts After a Benchmark Revision

• Activity Number: 394 - Time Series, Reconciliation, and National Statistics
• Type: Topic Contributed
• Date/Time: Tuesday, August 1, 2017 : 2:00 PM to 3:50 PM
• Sponsor: Government Statistics Section
• Author(s): Baoline Chen* and Tommaso Di Fonzo and Thomas Howells and Marco Marini
• Companies: Bureau of Economic Analysis and University of Padova and Bureau of Economic Analysis and International Monetary Fund
• Keywords: Benchmarking ; Reconciliation ; Temporal and Contemporaneous Constraints ; Input-output Accounts

Abstract

In this study the 2003-2007 U.S. annual input-output (IO) accounts, GDP-by-industry accounts and expenditure-based GDP are reconciled with the 2002 and 2007 quinquennial benchmarks and all contemporaneous constraints of the IO accounts for the in-between years. The series are adjusted at the most disaggregated production level of details (NAICS 6-digit) according to statistical procedures able to deal with large systems of accounts subject to both temporal and contemporaneous constraints and able to account for reliabilities of source data. Our aim is to adjust the preliminary levels of the series using a simultaneous least-squares procedure based on the proportional first difference criterion, a movement preservation principle proposed by Denton (1971), such that they (i) are consistent with the quinquennial benchmarks available, (ii) fulfill all the accounting relationships for any given year, and (iii) show movements that are as close as possible to the preliminary information. We conduct a sensitivity analysis of the impact of reliabilities of preliminary estimates on the reconciled results. We also evaluate the proposed procedure with alternative procedures.