How was the Gallup/MIPT terrorism study conducted?

Results for the survey were based on telephone interviews with a sample of 2,519 adults, aged 18 and older. The survey used a random-digit dial telephone methodology designed to provide equal probabilities of selection for all households with telephones and every adult within a selected household. This methodology produced data that approximate the opinions of the general population of U.S. adults living in telephone households.

Four independent samples were initially generated representing the continental United States as a whole as well as oversamples of the New York City, Washington, D.C., and Oklahoma City Metropolitan Statistical Areas. The unweighted data contain results of 548 respondents from New York City, 529 from Washington D.C., 508 from Oklahoma City and 934 from the remaining contiguous United States for an overall sample of 2,519.

All national estimates were derived from the weighted dataset of all interviews combined proportional to the actual geographic distribution of adults living in telephone households in the continental United States as well as adjusted to reflect the U.S. Census Bureau estimates of age, gender, race and ethnicity within a region.

The survey was conducted between Jan. 28 and March 22, 2002, five to six months after the Sept. 11 attacks. The Gallup Organization and the University of Oklahoma Department of Psychiatry jointly designed the methodology of the survey. For results based on this sample, one can say with 95% confidence that the maximum error attributable to sampling and other random effects is ±2% for the national results and ±4% for each of the cities. In addition to sampling error, question wording and practical difficulties in conducting surveys can introduce error or bias into the findings of public opinion polls.