Results for this survey are based on telephone interviews conducted with a nationally representative sample of adults, ages 18 years and older, living in continental U.S. telephone households. The sample design included an oversample of African-American and Hispanic respondents as well an oversample of 18 to 49 year olds. To allow for separate analysis of African-American and Hispanic respondents, a disproportionate number of area code-exchange combinations with higher than average densities of African-American and Hispanic households were sampled. The oversample of 18 to 49 year olds was achieved by screening selected replicates for age-appropriate respondents. The data are weighted to produce a final sample that is representative of the general population of adults in the continental United States.

  • Interviews conducted Feb. 16 – Mar. 14, 2007
  • 2,020 interviews
  • Margin of sampling error is plus or minus 3 percentage points for results based on the total sample at the 95% confidence level. The margin of sampling error is higher for results based on subgroups of respondents.

Survey interviews conducted under the direction of Princeton Survey Research Associates International. Interviews were conducted in English and Spanish.

Bear in mind that question wording and practical difficulties in conducting surveys can introduce error or bias in the findings of opinion polls.