Source and Accuracy Statements

Data presented in this issue of OmniStats are from the November BTS Omnibus Household Survey collected November 3 through November 11, 2001. Data are preliminary and are subject to change. Data for the survey were gathered from approximately 1000 randomly selected households. Omnibus data are weighted to allow inferences about the target population: the noninstitutionalized population, aged 18 years or older who are currently living in the United States. Because these data come from a sample, they are subject to both sampling and nonsampling error. The accuracy of estimates depends on both types of error. Sampling error is the error caused by using a sample instead of conducting a census of the population and may affect the reliability of an estimate. Nonsampling error can affect both the reliability and accuracy of an estimate and is more difficult to measure. The most general categories of nonsampling error are coverage error, nonresponse error, response error, processing error, and estimation error. The full extent of nonsampling error is unknown. BTS will be conducting a follow-up survey in December for information about travel during Thanksgiving. The results of that survey will be available in mid-December. The Thanksgiving travel survey was part of a monthly survey BTS conducts to learn about people's travel habits and their attitudes about transportation issues. For additional information about the survey, please contact Liz Grossman, liz.grossman@bts.gov. Press contact: Dave Smallen, david.smallen@bts.gov.