The Census Bureau of the Department of Commerce announced today that the estimate of U.S. retail e-commerce sales for the third quarter of 2003, not adjusted for seasonal, holiday, and trading-day differences, was $13.291 billion, an increase of 27.0 percent (±4.2%) from the third quarter of 2002. Total retail sales for the third quarter of 2003 were estimated at $872.5 billion, an increase of 6.1 percent (±0.3%) from the same period a year ago.

The third quarter 2003 e-commerce estimate increased 6.6 percent (±1.5%) from the second quarter of 2003 while total retail sales increased 1.6 percent (±0.3%) from the prior quarter.

E-commerce sales in the third quarter of 2003 accounted for 1.5 percent of total sales, while in the third quarter of 2002
e-commerce sales were 1.3 percent of total sales. In the second quarter of 2003 e-commerce sales were 1.5 percent of total sales.

Release dates for 2004 are February 23, May 21, August 20, and November 19.

billions of dollars

E-commerce retail sales data and frequently asked questions (FAQ’s) about e-commerce sales are available on the Census website at www.census.gov/mrts/www/mrts.html. For additional information about Census Bureau e-business measurement programs and plans visit www.census.gov/estats.

Table 1.Estimated Quarterly U.S. Retail Sales¹: Total and E-commerce
(Data in millions of dollars, not adjusted for seasonal, holiday, and trading-day differences.)

NA Not available. ^r Revised. ^p Preliminary.

¹ Does not include Food Services.

² E-commerce sales are sales of goods and services where an order is placed by the buyer or price and terms of sale are negotiated over an Internet, extranet, Electronic Data Interchange (EDI) network, electronic mail, or other online system. Payment may or may not be made online.

Explanatory Notes

Retail e-commerce sales are estimated from the same sample used in the Monthly Retail Trade Survey (MRTS) to estimate preliminary and final U.S. retail sales. Advance U.S. retail sales are estimated from a subsample of the MRTS sample that is not of adequate size to measure changes in retail e-commerce sales.

A stratified simple random sampling method is used to select approximately 11,000 retail firms whose sales are then weighted and benchmarked to represent the complete universe of over two million retail firms. The MRTS sample is probability based and represents all employer firms engaged in retail activities as defined by the North American Industry Classification System (NAICS). Coverage includes all retailers whether or not they are engaged in e-commerce. Online travel services, financial brokers and dealers, and ticket sales agencies are not classified as retail and are not included in either the total retail or retail e-commerce sales estimates. Nonemployers are represented in the estimates through the benchmarking operation. E-commerce sales are included in the total monthly sales estimates.

The MRTS sample is updated on an ongoing basis to account for new retail employer businesses (including those selling via the Internet), business deaths, and other changes to the retail business universe. Research was conducted to ensure that retail firms selected in the MRTS sample and engaged in e-commerce are representative of the universe of e-commerce retailers.

Firms are asked each month to report e-commerce sales separately. For each month of the quarter, data for nonresponding sampling units are imputed from responding sampling units falling within the same kind of business and sales size category. Approximately 14 percent of the e-commerce sales estimate for third quarter 2003 was imputed. Imputed total retail sales data accounted for approximately 20 percent of the estimate of U.S. retail sales for the third quarter 2003.

For each month of the quarter, estimates are obtained by summing weighted sales (either reported or imputed). The monthly estimates are benchmarked to prior annual survey estimates. Estimates for the quarter are obtained by summing the monthly benchmarked estimates. For third quarter 2003, the estimate for September is a preliminary estimate. Therefore, the estimate is subject to revision.


Reliability of Estimates

The margin of error for the change in U.S. retail e-commerce sales from the second quarter 2003 to the third quarter 2003 is approximately 1.5%, giving a range of +5.1% to +8.1%. Range estimates are computed based on the particular sample selected and canvassed. If we had repeated the process of drawing all possible samples and forming all corresponding range estimates, approximately 90 percent of these individual range estimates would have contained the quarter-to-quarter change in e-commerce sales computed from a complete enumeration of all retail firms on the sampling frame. Because the range above does not contain 0%, we can conclude at the 90 percent confidence level that retail e-commerce sales increased from the second quarter 2003 to the third quarter 2003.

Estimates in this report are based on a sample, and therefore, are subject to sampling and nonsampling error. A general discussion of the estimates and survey methodology appears in BR/02-A Current Business Reports and on the Internet: http://www.census.gov/mrts/www/mrts.html.


The U.S. Census Bureau, pre-eminent collector and disseminator of timely, relevant, and quality data about the people and the economy of the United States, conducts a population and housing census every 10 years, an economic census every five years, and more than 100 demographic and economic surveys every year, all of them evolving from the first census in 1790.