TheSupportingStatement2008[1]

The Supporting Statement

New England Transportation Institute

Part B. Collections of Information Employing Statistical Methods

1. Describe potential respondent universe and any sampling selection method to be used.

The respondent universe for both surveys is the general population of residents of the northeast U.S. The first survey (rural safety) will use a commercial online panel. It will oversample young males (between 18 and 28) living in the rural areas. The second survey (rural mobility) will use an address-based sample and will also oversample northeast residents living in non-metropolitan, rural areas.

2. Describe procedures for collecting information, including statistical methodology for stratification and sample selection, estimation procedures, degree of accuracy needed, and less than annual periodic data cycles.

The surveying process to be employed in this project has been used by members of the research team in many other studies of transportation behavior that incorporate both attitudes and beliefs together with more traditional transportation planning data. Each of the 2200 participants in the project will provide descriptions of their recent travel behavior, and answer questions on a seven point Rickert scale concerning their attitudes and beliefs that may or may not impact their travel behavior. The results reflect the respondent universe – i.e. travelers in the rural northeast--- and are not intended to represent and kind of random sample of the population in general.


3. Describe methods to maximize response rate.

NETI will employ the Dillman* method to maximize response rate. Dillman has developed a comprehensive approach to designing surveys that results in high response rates and highly-engaged respondents. RSG has successfully used this method (and its predecessor method that focused on mail-only surveys) for 20 years. The general approach draws on elements of social psychology that deal with “social exchanges” and uses all aspects of the survey’s design – from the wording on invitations to fonts used in questionnaires – to encourage participation. Modest tangible incentives will be used to reinforce the value that the researchers place on respondents’ participation.

For the address-based sample, the Dillman method will be applied as follows:

1. Week 1: A pre-notice letter, containing a one dollar incentive, will be mailed first class to all potential participants to alert them that they will be receiving the survey in a few days.

2. Week 1: Professionally designed paper-based survey with business reply mail will be mailed first class to all potential participants. The paper-based survey will contain instructions for completing the survey online if the respondent prefers that method.

3. Week 2: A reminder postcard will be sent one week after the paper-based survey to encourage participation by those who have not yet completed the survey.

4. Week 3: If quotas have not been reached, a second paper-based survey will be mailed to all who have not yet completed the survey.

* Don Dillman: Mail and Internet Surveys: The Tailored Design Method, Wiley, 2000.

4. Describe tests of procedures or methods.

Small survey pilots will be used to test the instruments and the response rates. Survey instruments are subjected to a survey pretest to ensure that respondents are able to understand and complete the survey questionnaire. Web-based responses are validated in real-time to ensure complete responses; data entry of paper-based surveys is checked by RSG staff. Web-based survey instruments are subjected to a battery of both automated and manual tests.

5. Provide name and telephone number of individuals who were consulted on statistical aspects of the IC and who will actually collect and/or analyze the information.

Thomas Adler, PhD

President

Resource Systems Group, Inc.

802-295-4999

Attachments:

An electronic PDF file has been included in this transmission containing the FHWA’s 60-day Federal Register notice, February 12, 2007, Page 6656. Volume 72 number 28. Docket number FHWA 2007-27203.