Results for the Late March War Tracking survey are based on telephone interviews conducted under the direction of Princeton Survey Research Associates among a nationwide sample of 2,708 adults, 18 years of age or older, during the period March 20-April 1, 2003. Results are reported separately for the periods of March 20-22 (N=903), March 23-24 (N=592), March 25-27 (N=539) and March 28-April 1 (N=674). Certain questions were asked only for the period of March 28-April 1.
For results based on March 20-22 and March 28-April 1, one can say with 95% confidence that the error attributable to sampling and other random effects is plus or minus 4 percentage points. For results based on March 23-24 and March 25-27, one can say with 95% confidence that the error attributable to sampling and other random effects is plus or minus 4.5 percentage points. In addition to sampling error, one should bear in mind that question wording and practical difficulties in conducting surveys can introduce error or bias into the findings of opinion polls.
The sample for this survey is a random digit sample of telephone numbers selected from telephone exchanges in the continental United States. The sample was released for interviewing in replicates, with fresh replicates introduced on each night of the tracking poll, and retired from the sample after five nights of interviewing. Non-response in telephone interview surveys produces some known biases in survey-derived estimates because participation tends to vary for different subgroups of the population, and these subgroups are likely to vary also on questions of substantive interest. In order to compensate for these known biases and ensure that tracking trends are not unduly influenced by demographic variation across the field period, the sample data for each period of the tracking poll (March 20-22, 23-24, 25-27 and 28-April 1) are weighted to approximate the demographic parameters derived from the most recently available Census Bureau’s Current Population Survey (March 2002).
Some of the demographic analyses in this report are based on aggregated samples in order to ensure an adequate number of cases in smaller subgroups. For analyses based on the current survey, the total “wartime” sample size of interviews from March 20-April 1 is 2,708. For analyses based on “pre-war” data, we have combined Pew Research Center surveys from December, January, February and early-March for a total sample of 4,102 cases. For details on sample sizes and error margins of specific demographic groups contact the center.