supporting statementB

SUPPORTING STATEMENT

BUREAU OF ECONOMIC ANALYSIS

SURVEY OF INTERNATIONAL TRAVEL EXPENDITURES

B. COLLECTIONS OF INFORMATION EMPLOYING STATISTICAL METHODS

1. Describe (including a numerical estimate) the potential respondent universe and any sampling or other respondent selection method to be used. Data on the number of entities (e.g. establishments, State and local governmental units, households, or persons) in the universe and the corresponding sample are to be provided in tabular form. The tabulation must also include expected response rates for the collection as a whole. If the collection has been conducted before, provide the actual response rate achieved.

The potential respondent universe is all U.S. residents who travel abroad and all foreign residents who travel to the United States, except travel to and from Mexico and Canada. Based on 2006 data from the Department of Homeland Security, the potential respondent universe is approximately 30 million for U.S. travelers and 22 million for foreign travelers. BEA will be surveying approximately 6,000 travelers; roughly half will be U.S. travelers and half foreign travelers.

	Potential respondent universe	Approximate number of completed surveys
Total	52 million	6,000
U.S. travelers	30 million	3,000
Foreign travelers	22 million	3,000

Respondents will be selected at a sample of U.S. international airports representing different regions of the United States. Ideally the probability of airport selection will be based on the number of travelers, but this may have to be adjusted based on the limitations imposed by the security regulations of certain airports. Interview times will be scheduled at each sample location to maximize the coverage by hour, by day of the week, and by time of year.

Once the airports are selected, respondents will be randomly selected. An interviewing rate will be applied based on the amount of traffic at each location – i.e. every 5^th person, every 10^th person, etc. – and the person selected for the interview will be approached.

Because the U.S. ITAs include geographical detail, there will be a target number of respondents for each of six major world regions (Europe, Latin America, Other Western Hemisphere, Asia and Pacific, Middle East, and Africa). The targets will assure that there will be adequate data for each of these regions to produce accurate estimates for the ITAs.

2. Describe the procedures for the collection, including: the statistical methodology for stratification and sample selection; the estimation procedure; the degree of accuracy needed for the purpose described in the justification; any unusual problems requiring specialized sampling procedures; and any use of periodic (less frequent than annual) data collection cycles to reduce burden.

The survey will be administered to U.S. travelers returning to the United States and foreign travelers leaving the United States. Travelers in a sample of U.S. international airports will be approached and their eligibility for the survey will be established orally by interviewers (or in writing for non-English speakers). There will be two very similar surveys – one for U.S. travelers and one for foreign travelers. For the U.S. traveler survey, eligible travelers will be those who live in the United States, who have completed travels abroad, and who have visited countries other than Canada and Mexico. For the foreign traveler survey, eligible travelers will be those who do not live in the United States, Canada, or Mexico, and who have completed a trip in the United States.

The survey itself will be a one-page self-administered survey. Respondents provide their age, gender, and primary purpose of trip (business/personal) to help assure adequate demographic coverage. A question on length of trip will help to identify travelers who were abroad for many months; these responses may be weighted differently in the estimates so that they do not overshadow the data of the majority of travelers on shorter trips. Respondents provide information on what world region they traveled to or from. The key data questions will ask travelers to report their travel expenditures excluding airfare by method of payment as a percentage of their total expenditures or in monetary terms. The survey will also ask respondents to identify whether their expenditures were paid for in advance of the trip or during the trip.

The survey will be conducted in four waves. Each wave will have targets for coverage of six major world regions (Europe, Latin America, Other Western Hemisphere, Asia and Pacific, Middle East, and Africa) to assure adequate sample for the geographic data published in the U.S. ITAs. To assure adequate coverage of these regions, interviewers may target certain airports or certain times of day. For this reason, traveler selection will not be completely random, but rather targeted to BEA’s particular needs.

3. Describe the methods used to maximize response rates and to deal with nonresponse. The accuracy and reliability of the information collected must be shown to be adequate for the intended uses. For collections based on sampling, a special justification must be provided if they will not yield "reliable" data that can be generalized to the universe studied.

BEA plans to maximize response rates by offering monetary incentives to respondents (described in item A9 above) and by approaching travelers in areas of the airports where they will be waiting, i.e., in departure lounges and in baggage claim. BEA has made every effort to keep the burden as low as possible, and will be translating the survey into several foreign languages.

To deal with non-response, interviewers will record the number of refusals and also the visible demographics – gender and age – of each selected person who refuses to participate in the survey. This information will be used to adjust for non-response by demographic.

4. Describe any tests of procedures or methods to be undertaken. Tests are encouraged as effective means to refine collections, but if ten or more test respondents are involved OMB must give prior approval.

Prior to fielding the survey, a survey pre-test will be conducted in one or two international airports to assure that the survey questions are clearly understood by respondents, to assess whether the respondents are providing accurate and reliable responses, and whether the survey instrument can be improved. Because BEA would like to survey more than 10 people in the survey test and because the survey plan includes offering an incentive (which its generic clearance for pretesting does not authorize), BEA will conduct the survey test once the OMB clearance process is complete.

5. Provide the name and telephone number of individuals consulted on the statistical aspects of the design, and the name of the agency unit, contractor(s), grantee(s), or other person(s) who will actually collect and/or analyze the information for the agency.

BEA’s Chief Statistician Dennis Fixler (202-606-9607) was consulted on statistical aspects of the design of the survey. The survey is designed and conducted by Charney Research of New York, NY. Contact Craig Charney or Justin Gale at 212-929-6933. At BEA, contact Michael Mann at 202-606-6573 or Patricia Abaroa at 202-606-9591.

3