|
|
|
|
Annual Revision of
Monthly Retail and Food Services
Explanation of Benchmarking
Revisions, Summary of Changes, and Definitions |
INTRODUCTION
The U.S. Census Bureau produces the Annual Revision of Monthly Retail and Food Services to provide
revised national estimates by kind of business of annual and monthly sales for establishments
classified in the retail trade and food services industries. Estimates of end-of-month inventories
and inventory-to-sales ratios are also provided, but only for retail trade.
We develop the estimates in this report
using data from the Advance
Monthly Retail Trade and Food Services Survey (MARTS), Monthly
Retail Trade Survey (MRTS), Annual
Retail Trade Survey (ARTS), and administrative records. For each
survey, questionnaires are mailed to a probability sample of firms located
in the United States and having paid employees. The samples are updated regularly
and periodically reselected. These samples include firms of all sizes. Firms
without paid employees (nonemployers) are included in the ARTS estimates through
administrative data provided by other Federal agencies and through imputation.
Additional information on MARTS, MRTS, and ARTS can
be found on the Census Bureau Web site at <http://www.census.gov/econ/www/retmenu.html>.
COVERAGE
The estimates in this publication are summarized by
industry classification based on the 2002
North American Industry Classification System (NAICS). NAICS groups
establishments into industries based on the activities in which they are primarily
engaged. This system, developed jointly by the statistical agencies of Canada,
Mexico, and the United States, allows for comparisons of business activity
across North America.
Retail trade, as defined by NAICS
sectors 44-45, includes establishments engaged in selling merchandise
in small quantities to the general public, without transformation, and rendering
services incidental to the sale of merchandise. Two principal types of establishments
classified in retail trade are distinguished:
1. Store
retailers operate fixed point-of-sale locations, located and designed to attract
a high volume of walk-in customers. They have extensive displays of merchandise,
use mass-media advertising to attract customers and typically sell merchandise
to the general public for personal or household use. Some store retailers
also provide after-sales services, such as repair and installation; for example,
new automobile dealers.
2. Nonstore
retailers also serve the general public, but their retailing methods differ.
Such methods include paper and electronic catalogs, door-to-door solicitation,
in-home demonstration, ‘‘infomercials,’’ selling from portable stalls or through
vending machines.
Food services, as defined by NAICS subsector 722, include
establishments that prepare meals, snacks, and beverages to customer
order for immediate on-premises and off-premises consumption.
A summary of changes from the prior report and
the procedures for producing the revised estimates are described below.
SUMMARY OF CHANGES
This report includes nine NAICS industries
not included in previous revisions. The not adjusted sales estimates for these
industries were first published as part of the January 2008 MRTS release.
The industries are:
• 44221 Floor covering stores
• 442299 All other home furnishing stores
• 44412 Paint and wall paper stores
• 44511 Supermarket and other grocery (except convenience) stores
• 44819 Other clothing stores
• 45112 Hobby, toy, and games stores
• 45321 Office supplies and stationary paper
• 45322 Gift, novelty, and souvenir stores
• 45330 Used merchandise stores
The estimates for these industries are
published from January 1992 to the current month with the exception of NAICS
442299, 44412, 44511, and 44819, which do not exist historically and thus
are published only from January 2001 forward.
REVISIONS TO PREVIOUSLY PUBLISHED ESTIMATES
Not adjusted estimates of monthly sales are revised
for January 2005 through February or March 20081 (if an advance sales estimate
is computed), as well as end-of-month inventory estimates for January 1999 through
February 2008. We revised the not adjusted estimates to:
• Reflect corrections to data for the current MRTS and
ARTS samples.
• Introduce results from the 2006 ARTS.
• Link the previously published estimates from the prior
sample to estimates from the current sample.
Annual sales estimates for 2005 are also revised due
to the availability of nonemployer sales data from administrative records provided
by other Federal agencies.
New seasonal, trading-day, and holiday factors are computed
and used to adjust sales for January 2002 through February or March 20081 (if
an advance sales estimate is computed). For inventories, new seasonal factors
are computed and used to adjust inventories for January 1996 through February
2008. Adjusted estimates start 3 years before the revised, not adjusted estimates
because these revised, not adjusted estimates can affect the computation of
seasonal factors as far back as 3 years ago. For both sales and inventories,
the new seasonal factors are computed using not adjusted estimates as input
to the seasonal adjustment program.
Annual Estimates
Totals estimated from the current sample survey are
computed as the sum of weighted data for all selected sampling units that meet
the tabulation criteria given in the Sample Maintenance section.
The weight for a given sampling unit is the reciprocal of its probability of
selection into the sample. The sample-based estimated totals from the current
sample are then linked to the estimates from the prior sample using the procedure
described on the Census Bureau Web site at <http://www.census.gov/svsd/www/summary.html>.
Estimates of Monthly Sales
For select detailed NAICS codes, corrections are applied
to the monthly retail and food service sales estimates for August 2006 through
February 2008. Then, for each detailed NAICS code, the monthly retail and food
service sales estimates for January 1992 (the beginning of the series) through
August 2006 from the prior sample are linked to the estimates derived from the
current sample. The linkage is performed for each detailed NAICS level by multiplying
the sample-based estimates, or unmodified estimates, from the prior sample by
a geometric mean. The geometric mean is computed as the square root of the product
of two ratios. The numerators of the ratios are the unmodified sales estimates
for August and September 2006 from the current sample. The denominators of the
ratios are the unmodified estimates for August and September 2006 from the prior
sample.
After performing the above linkage, the resulting sales estimates for December
2004 through February 2008 are input to the benchmarking program. The estimates
for a given detailed NAICS code are revised in a manner that—
• For 2005 and 2006, constrains the sum of the 12 monthly sales estimates to
equal the corresponding annual sales estimate from ARTS.
• Minimizes the sum of the squared differences between the month-to-month changes
of the input and revised estimates for December 2004 through February 2008.
• Uses the previously published December 2004 sales estimate as a constraint,
linking the revised estimates to the previously published sales estimates and
resulting in no revision to the December 2004 estimate.
If an advance sales estimate is computed for an industry, the March 2008 estimate
is revised using the previously estimated month-to-month ratio (from the originally
published MARTS release on April 14, 2008). This ratio is applied to the revised
February 2008 sales estimate output from the benchmarking to obtain a new March
sales estimate. For more information on how advance estimates are computed,
see the Census Bureau Web site at <http://bhs.econ.census.gov/BHS/RTFS/About.html>.
A mathematical result of the benchmarking methodology
is that all revised estimates following the end of the last benchmark year (2006)
are derived by multiplying the corresponding input estimates by the ratio of
the benchmarked-to-input estimate for the last month of the last benchmark year.
Therefore, for a given NAICS code, a ratio of the benchmarked-to-input estimate
for December 2006 is computed. Monthly sales estimates after December 2006 are
multiplied by this constant ratio, which is called a carry-forward factor, to
derive published sales estimates. The carry-forward factor remains the same
until the next benchmarking operation.
Revised estimates for aggregate industry levels are computed by summing the
revised estimates for the appropriate detailed industries comprising the aggregate.
Estimates of End-of-Month Inventories
For select detailed NAICS codes, corrections are applied
to the monthly retail end-of-month inventory estimates for August 2006 through
February 2008. Then, for each detailed NAICS code, the monthly retail end-of-month
inventory estimates for January 1992 (the beginning of the series) through August
2006 from the prior sample are linked to the estimates derived from the current
sample. The linkage is performed using a procedure similar to the one used for
sales, except the geometric mean is based on end-of-month inventory.
After performing the above linkage, the resulting end-of-month inventory estimates
for December 1998 through February 2008 are input to the benchmarking program.
The estimates for a given detailed NAICS code are revised in a manner that—
• For 1998 through 2006, constrains the December end-of-month inventory estimates
from MRTS to equal the end-of-year inventory estimates derived from ARTS.
• Minimizes the sum of squared differences between the month-to-month changes
of the input and revised estimates for December 1998 through February 2008.
• Uses the previously published December 1998 estimate as a constraint, linking
the revised estimates to the previously published estimates and resulting in
no revision to the December 1998 estimate.
For a given detailed NAICS code, end-of-month inventory
estimates subsequent to December 2006 are derived by multiplying the input estimates
by the ratio of the benchmarked-to-input estimate for December 2006. This ratio
is the carry-forward factor for inventory, and it remains the same until the
next benchmarking operation.
Revised estimates for aggregate industry levels are
computed by summing the revised estimates for the appropriate detailed industries
comprising the aggregate.
REVISIONS OF SALES AND INVENTORIES
The following table shows a comparison of the revised
sales and inventories to the previously published estimates for 2007:
2007
Retail and Food Services Sales and Retail Inventories Comparison of the Revised
Estimates
to the Previously Published Estimates
Reasons for Revisions
There are several reasons for revisions. The main contributors
to the revision from the previously published estimates are:
- Timing.
The respondents have more time to prepare their annual and census
reports than they do for their monthly reports. The annual and census responses
are requested at a time when many firms have already compiled audited book
figures for their own use. The timing of the annual survey is such that we
are also able to obtain independent verification of the reported data from
such sources as a company’s annual report. On the other hand, respondents
to the monthly survey have just a few weeks to provide reports of their sales
and end-of-month inventories. Sometimes these reports are based on incomplete
or unaudited records and may include estimates made by respondents to represent
their understanding of their business.
- Sample
Size. As described in more detail in the Technical
Documentation section of this report, the estimates derived from the annual
survey are based on a sample that is much larger than the samples used to
produce the monthly sales or inventory estimates. Furthermore, the monthly
inventory estimates are based on a sample with fewer units than the sample
used to produce the monthly sales estimates.
- Response.
The annual estimates are based on more reported data than are the
monthly estimates. The response to the ARTS
is required by law. This requirement results in a dollar volume response rate
for sales above 94 percent. The response to our monthly
survey is not mandatory. The dollar volume response rates for the monthly
surveys are usually around 78 percent for sales and 72 percent for inventories.
The sales and inventories for the nonresponding retailers are accounted for
by an imputation process. This process on the monthly surveys assumes that
nonresponding firms have trends similar to the responding firms in their respective
kinds of business.
DEFINITION
OF TERMS
Dollar Values
All dollar values presented are expressed in current
dollars; that is, the estimates are not adjusted to a constant dollar series.
Consequently, when comparing estimates to prior years, users also should consider
price level changes.
Confidentiality
Title 13 of the United States Code authorizes the Census
Bureau to conduct censuses and surveys. Section 9 of the same Title requires
that any information collected from the public under the authority of Title
13 be maintained as confidential. Section 214 of Title 13 and Sections 3559
and 3571 of Title 18 of the United States Code provide for the imposition of
penalties of up to 5 years in prison and/or up to $250,000 in fines for wrongful
disclosure of confidential census information. In accordance with Title 13,
no estimates are published that would disclose the operations of an individual
firm.
The Census Bureau's Internal Disclosure Review board
sets the confidentiality rules for all data releases. A checklist approach
is used to ensure that all potential risks to the confidentiality of the data
are considered and addressed.
Disclosure Limitation
A disclosure of data occurs when an individual can use
published statistical information to identify either an individual or firm that
has provided information under a pledge of confidentiality. Disclosure limitation
is the process used to protect the confidentiality of the survey data provided
by an individual or firm. Using disclosure limitation procedures, the Census
Bureau modifies or removes the characteristics that put confidential information
at risk for disclosure. Although it may appear that a table shows information
about a specific individual or business, the Census Bureau has taken steps to
disguise or suppress the original data, while making sure the results are still
useful. The techniques used by the Census Bureau to protect confidentiality
in tabulations vary, depending on the type of data.
Unpublished Estimates
Additional statistics, such as dollar volume estimates
for some kinds of business not separately shown in this report, are produced
as a by-product of the regularly published statistics. These additional estimates
have not been included in this publication because of high sampling variability,
poor response, or other factors that may make them potentially misleading. It
should be noted that some unpublished estimates can be derived directly from
this report by subtracting published estimates from their respective totals.
However, the estimates obtained by such subtraction would be subject to the
poor response rates or high sampling variability described previously for unpublished
kinds of business.
Individuals who use estimates in this report to create
new estimates should cite the Census Bureau as the source of only the original
estimates.
Adjustment Factors
The
X-12 ARIMA program was used to derive the factors for adjusting estimates
for seasonal variations and, in the case of sales, for trading-day and holiday
differences. Not adjusted sales and inventory estimates for January 1992 through
February or March 20081 (if an advance sales estimate was computed)
were input to this program.
Seasonal adjustment of estimates is an approximation
based on current and past experiences. Therefore, the adjustment could become
less precise because of changes in economic conditions and other elements that
introduce significant changes in seasonal, trading-day, or holiday patterns.
Sales
Sales include merchandise sold (for cash or credit at
retail or wholesale) by establishments primarily engaged in retail trade. Services
that are incidental to the sale of merchandise, and excise taxes that are paid
by the manufacturer or wholesaler and passed along to the retailer are also
included. Sales are net, after deductions, for refunds and allowances for merchandise
returned by customers. Sales exclude sales taxes collected directly from customers
and paid directly to a local, state, or federal tax agency.
The estimates of sales measure the operations receipts
rendered by stores that primarily sell at retail. The sales estimates represent
total sales and receipts of all establishments primarily engaged in retail trade.
They do not include sales at retail by manufacturers, wholesalers, service establishments,
and others whose primary activity is other than retail trade. Because the retail
establishment is the basic unit of measure, the published estimates of sales
by type of retail store are not intended to measure the total sales for a given
commodity or merchandise line.
Inventories
Merchandise inventories are the value of stocks of goods
held for sale. The inventories estimates represent the value, at cost, of the
merchandise available for sale as of the last day of the report period. Methods
of valuation may vary according to the accounting practices of each firm. The
estimates provided in this report are valued on a non-LIFO (last in, first out)
basis. Note—LIFO is a method of valuing inventory where the latest items of
merchandise added to the inventory are the first ones taken out. Non-LIFO would
mean that another method, such as FIFO (first in, first out), was used to establish
the value of the inventory available for sale. Merchandise inventories are shown
for stores and warehouses servicing retail establishments. Included are only
those warehouses that maintained supplies of merchandise primarily intended
for distribution within the organization.
Inventories/ Sales Ratios
The inventories/ sales ratios show the relationship
of the end-of-month values of inventory to the monthly sales. These ratios can
be looked at as indications of the number of months of inventory that are on
hand in relation to the sales for a month. For example, a ratio of 2.5 would
indicate that the retail stores have enough merchandise on hand to cover two
and a half months of sales.
