Printer Friendly

The statistics producers' corner.


The Census Bureau, which is responsible for compiling and publishing U.S. merchandise trade data from Shipper's Export Declarations filed with the U. S. Customs Service, estimates that data collection and reporting errors result in a 3 to 7 percent understatement of total export value. Several approaches are being taken by the Census Bureau and the Customs Service to reduce these errors. The most important step is the Customs Service's development, with Census Bureau assistance, of the Automated Export System (AES) for export administration and data collection.

Sources of Error

The three major sources of trade exports error are: (1) failure of exporters to file the required documentation; (2) missing or incorrect information reported on the documents that are filed; and (3) late receipts of export records sent to the Census Bureau.

Failure to file the required export documentation has been a long-standing problem, particularly for overland and parcel trade. In addition, some exporters may not be fully aware of export reporting requirements. A 1992 analysis of one month's export reporting showed that roughly half of all paper documents contained at least one error. Although most of this missing or incorrect information does not affect the value of exports or the balance of trade, it can significantly affect detailed commodity and transportation analyses.

Late receipts occur when paper documents are not received by the Census Bureau in time for inclusion in the correct statistical month. At one point in the mid-1980s, such late receipts or "carryover" averaged 10 percent of any month's export value. Through the joint efforts of the Census Bureau and the Customs Service, carryover is now less than 1 percent in most months. However, the logistical problems involved in processing each month 500,000 paper documents from hundreds of customs ports can cause sharp fluctuations in the carryover value and significant changes in the trade balance.

Steps Underway to Improve Quality

The AES should directly address all three of these problems, resulting in significantly better export data. However, no one solution will resolve all of the issues affecting the quality and coverage of the export statistics. In addition, the Census Bureau and Customs Service are conducting extensive outreach and education programs to make exporters aware of their obligations to file. The Customs Service has also launched an expanded "informed compliance" effort to ensure that exporters correctly file the required information.

Full implementation of the AES, which will take place in July 1997, is the single most important step that can be taken to improve the accuracy and coverage of export statistics. This system will improve data collection and data quality by: (1) eliminating the delays and logistical problems associated with collecting paper documents; (2) permitting the reconciliation of individual shipments against electronic manifests for all methods of transportation to ensure complete coverage; and (3) editing data as they are received so that the filer can correct incomplete or invalid information prior to statistical processing.

The early evidence is that AES significantly reduces the amount of incomplete or invalid information received. Currently AES participants file data through the system for about 2500 shipments each month. Up-front edits and warning messages prompt corrections by filers, so that, when the Census Bureau processes the data, very few errors are found. For example, in a recent month only fourteen shipments out of 2560 failed the processing edits.

A more extensive error analysis was done during the evaluation of AES late in 1996. Throughout the dual reporting period (when companies reported the same data through AES and their previous reporting method), less than 9 percent of the AES entries contained questionable information. This is a dramatic improvement compared to the information reported on paper documents, where roughly half of the records contained one or more errors.

In addition, when the extracted records were submitted to further edits at the Census Bureau, less than 0.6 percent were rejected. Again, these results compare favorably with data filed through the current antiquated automated system or on Shipper's Export Declarations, which have average reject rates of 1.6 percent and 0.7 percent, respectively.

For additional information on the AES, contact Anita Brown of the Census Bureau at (voice) 301-457-2207, (fax) 301-457-1159. For more information on U.S. merchandise trade data, contact Richard Preuss of the Census Bureau (voice) 301-457-2311, (fax) 301-457-2645.


The Bureau of Labor Statistics (BLS) has introduced an experimental Consumer Price Index (CPI) for All Urban Consumers, or CPI-U-XG, that uses a geometric mean formula to combine individual price quotations at the lower level of aggregation while keeping the current Laspeyres (fixed weight) for higher level aggregation. The new series begins with December 1990.

The CPI-U and CPI-W are calculated using a fixed-weight Laspeyres formula and do not reflect the fact that consumers can and do change spending patterns as relative prices change. Under certain assumptions, a measure of change in consumer prices that uses a geometric mean formula will successfully account for this consumer behavior. To the extent that those assumptions are accurate, the index using geometric means will provide a closer approximation to a cost-of-living index.

In addition to differences between the CPI-U and CPI-U-XG that arise because of the different formulas used, there also are differences because of methodological changes made in the CPI-U since 1990 that are reflected in the CPI-U-XG for the entire series. For historical comparison to the CPI-U-XG, therefore, BLS also has issued an experimental test Laspeyres series, the CPI-U-XL, which differs from the CPI-U-XG only in the use of the Laspeyres formula for aggregation of price quotations.

From December 1990 to February 1997, the CPI-U-XG rose 16.2 percent, compared with 18.6 percent for the CPI-U-XL. The average annual rate of growth in the CPI-U-XG over this period was 2.46 percent, 0.34 percentage points lower than the 2.80 percent annual growth rate of the CPI-U-XL. Among major item groups, the largest differences between the two indexes were in food and beverages, apparel and upkeep, medical care, and entertainment. Because the January 1995 methodological changes in the CPI treatment of food at home appear to have reduced the difference between the CPI-U-XG and CPI-U-XL, BLS expects a further narrowing of the gap as a result of additional changes made in June and July of 1996.

The experimental indexes are being studied as part of a BLS research program to evaluate, item category by item category, adoption of the geometric mean formula in all or some components of the official CPI. Scanner data and other information will be used to assess the propensity of consumers to substitute across items within individual item categories as the relative prices of those items change. By the end of 1997, BLS will announce the findings of its research, including its determination of which CPI basic indexes are best calculated with the geometric mean formula.

The new indexes are released one week after the release of the featured indexes. The most recent monthly data are available on the Internet at and also are included quarterly in the CPI Detailed Report. For further information, write to the BLS, Division of Consumer Prices and Price Indexes, Room 3615, 2 Massachusetts Ave. NE, Washington, DC 20212-0001, or call Kenneth J. Stewart at 202-606-7000.

This material has been compiled and edited by Robert P. Parker and C. Brian Grove, Bureau of Economic Analysis, U.S. Department of Commerce, Washington, DC.
COPYRIGHT 1997 The National Association for Business Economists
No portion of this article can be reproduced without the express written permission from the copyright holder.
Copyright 1997 Gale, Cengage Learning. All rights reserved.

Article Details
Printer friendly Cite/link Email Feedback
Publication:Business Economics
Date:Jul 1, 1997
Previous Article:The statistics corner: update on the BLS sample redesign for the current employment statistics survey.
Next Article:The business economist at work: KPMG Peat Marwick LLP.

Terms of use | Privacy policy | Copyright © 2020 Farlex, Inc. | Feedback | For webmasters