Annual Benchmark Report for Retail Trade:

Summary of Changes

 

Annual sales estimates for 2006 are revised due to the availability of nonemployer sales data from administrative records provided by other Federal agencies. Additionally, starting with survey year 2006, the Annual Retail Trade Survey (ARTS) collects total operating expenses for retail establishments.

 

Revisions to Previously Published Estimates

 

Sales estimates for 2005 and subsequent years are adjusted to the 2002 Economic Census by linking the estimates from the current sample to the published census-adjusted estimates from the prior sample. Prior to adjustment, historical corrections are made to current sample data back to 2004. For a given detailed industry based on the 2002 North American Industry Classification System (NAICS), the linking is performed by multiplying the sample-based sales estimate by a ratio. The numerator and denominator of the ratio are as follows:

 


§         The numerator is the 2004 published census-adjusted sales estimate for the industry from the prior sample.

 

§         The denominator is the 2004 sales estimate for the industry from the current sample.

 

The expenses estimates for 2006 and subsequent years are adjusted by applying the ratio described above for each detailed industry. A method similar to the one for adjusting sales is used to link the end-of-year inventories and purchases estimates. First, the ratio described above is applied to the sample-based estimates for the given detailed industry for 2004 and subsequent years, resulting in adjusted estimates for these years. Then, the published adjusted estimates for 1998 through 2004 from the prior sample are input to the benchmarking program. Using this program, the estimates for 1999 through 2004 are revised in a manner that:

 


 

§         Uses the published adjusted estimate for 1998 from the prior sample as a constraint, resulting in no revision to the published 1998 estimate.

 

§         Uses the adjusted estimate for 2004 from the current sample as a constraint.

 

§         Minimizes the sum of squared differences between the year-to-year changes of the input and revised estimates for 1999 through 2004.

 

Estimates for e-commerce sales are revised in a manner similar to the method used to adjust inventories and purchases.

 

Estimates at 2-, 3-, 4-, and 5-digit NAICS levels are computed by summing the adjusted estimates for the appropriate detailed industries comprising the aggregate. Accounts receivable estimates for 2004 and subsequent years are produced directly from the current sample and are not adjusted.