Hurricanes Katrina and Rita FAQ for September 2005
Can the Census Bureau estimate the effect of Hurricane Katrina on the sales estimates?
No. We cannot isolate the effect of Hurricane Katrina on the Advance Monthly Retail Trade and Food Services Survey (MARTS) estimates since the sample is designed to measure retail and food services activity at the national level and not at specific geographic areas.
Even though we cannot isolate the effect, we did receive indications from the companies that the hurricanes had both positive and negative effects on the retail sales data. Some firms reported a drop in sales due to permanent or temporary store closures and stores having reduced business due to damage, fewer customers, and/or lack of employees. On the other hand, some firms reported sales increases due to significant sales of supplies for the affected areas and stores reopening in the affected areas.
The areas most affected by the hurricanes ordinarily account for a minimal percentage of total U.S. retail and food services sales based on the 2002 Economic Census. See http://www.census.gov/econ/www/Katrina.htm for data from the 2002 Economic Census for the Gulf Coast areas affected by Hurricane Katrina.
Was the Census Bureau able to collect information from firms operating within the affected areas?
Yes. In Louisiana, Mississippi, and
Alabama, company response was in a normal range. Further, many large, regional,
and other multi-location firms with reporting offices outside the affected states
responded at a normal rate and included sales data for stores, both open and
closed, located in the affected areas.
Did the Census Bureau modify its non-response or estimation procedure?
No. Ordinarily, no imputation is done for individual nonrespondents. The MARTS survey accounts for missing data when estimating industry totals. The estimate makes use of data from MARTS respondents that report sales data for both the current and prior month and applies the resulting month-to-month change to the prior month sales estimates from the Monthly Retail Trade Survey (MRTS). The MRTS imputes missing data for nonresponding firms based on reported data from firms that are in the same industry and the same size category as the nonrespondents.
The estimation procedure assumes that for a given industry the month-to month change for firms that report is similar to the month-to-month change for firms that do not report. This assumption is supported if sufficient reports from the affected area are received or if the reports received are representative of the area.
Has the reliability of the sales estimate changed because of the hurricane?
No, the reliability has not changed substantially. At the national level, reported sales exhibited variation similar to that for prior months. A few individual firms reported large increases or decreases in their sales because of the effects of the hurricane, but this additional variation was not large enough to affect the reliability of national estimates.
Did the Census Bureau alter the seasonal adjustment options?
No. The review of the seasonal adjustment output and diagnostics did not indicate that adjustments to the options were necessary.
For additional information regarding specific months, click on the following links to previous FAQs:
Hurricanes Katrina and Rita FAQ for September 2005 Hurricane Katrina FAQ for August 2005
Source: U. S. Census Bureau
Service Sector Statistics Division
Last Revised: November 14, 2005