Trump Draws Stronger Support From Veterans Than From the Public on Leadership of U.S. Military
This study included both a general population sample of U.S. adults and a sample of U.S. military veterans. The sample of U.S. adults (n=1,087) was fielded using the KnowledgePanel, which is a probability-based online survey panel maintained by Ipsos. The target population for the general population sample was non-institutionalized adults age 18 and over, living in the US, including Alaska and Hawaii.
In order to achieve a reliable sample size of U.S. veterans, two online probability-based based were used: both KnowledgePanel and Pew Research Center’s American Trends Panel. The subsample from the ATP was selected by sampling all active panelists who reported being a veteran in the annual profile survey. All active panelists from Ipsos’ KnowledgePanel that reported being a veteran were sampled. KnowledgePanel veterans were screened and allowed to fully complete the survey if they confirmed they were a veteran that served after September 11 (post-9/11). In total, 1,284 veterans responded to the survey.
The general population survey was conducted May 14 to May 24, 2019 and the veteran survey was conducted May 14 to June 3, 2019. Interviewing was conducted in both English and Spanish.
KnowledgePanel members are recruited through probability sampling methods and include those with internet access and those who did not have internet access at the time of their recruitment (KnowledgePanel provides internet access for those who do not have it, and if needed, a device to access the internet when they join the panel). A combination of random-digit dialing (RDD) and address-based sampling (ABS) methodologies have been used to recruit panel members (in 2009 KnowledgePanel switched its sampling methodology for recruiting members from RDD to ABS). KnowledgePanel continually recruits new panel members throughout the year to offset panel attrition as people leave the panel.
The American Trends Panel (ATP), created by Pew Research Center, is a nationally representative panel of randomly selected U.S. adults. Panelists participate via self-administered web surveys. Panelists who do not have internet access at home are provided with a tablet and wireless internet connection. The panel is being managed by Ipsos.
The ATP was created in 2014, with the first cohort of panelists invited to join the panel at the end of a large, national, landline and cellphone random-digit-dial survey that was conducted in both English and Spanish. Two additional recruitments were conducted using the same method in 2015 and 2017, respectively. Across these three surveys, a total of 19,718 adults were invited to join the ATP, of which 9,942 agreed to participate.
In August 2018, the ATP switched from telephone to address-based recruitment. Invitations were sent to a random, address-based sample (ABS) of households selected from the U.S. Postal Service’s Delivery Sequence File. In each household, the adult with the next birthday was asked to go online to complete a survey, at the end of which they were invited to join the panel. For a random half-sample of invitations, households without internet access were instructed to return a postcard. These households were contacted by telephone and sent a tablet if they agreed to participate. A total of 9,396 were invited to join the panel, and 8,778 agreed to join the panel and completed an initial profile survey. Of the 18,720 individuals who have ever joined the ATP, 13,462 remained active panelists and continued to receive survey invitations at the time this survey was conducted.
The U.S. Postal Service’s Delivery Sequence File has been estimated to cover as much as 98% of the population, although some studies suggest that the coverage could be in the low 90% range.3
Out of 7,570 who were sampled, 3,758 were eligible to take the survey, out of which a total of 2,371 panelists responded, for a response rate of 63.1%. This included 971 ATP members and 1,400 respondents sampled from Ipsos’ KnowledgePanel. This does not include seven respondents who were removed from the data due to extremely high rates of refusal or straightlining and two who were removed after they were deemed ineligible based on an open-ended response given when asked which branch of the military they served in. The cumulative response rate accounting for nonresponse to the recruitment surveys and attrition is 1.6%. The break-off rate among panelists who logged onto the survey and completed at least one item is 1%. The margin of sampling error for the sample of 1,284 veteran respondents is plus or minus 3.9 percentage points. The margin of sampling error for the sample of 1,087 general population respondents is plus or minus 3.1 percentage points.
The final survey dataset contains two sample weight variables: one for the total general population adult sample and one for the total combined ATP+KP veteran sample. Each weight was created with a base weight reflecting the probability of selection followed by calibration to known demographics of the target population.
For the Veterans weight, Ipsos scaled the KP and ATP base weights proportional to effective sample size. Then they downweighted the combined ATP and KP post-9/11 Veterans to be 19.42% of the combined sample (based on ACS benchmark). Finally, the weight was raked to benchmark veteran population demographic targets computed from the 2017 American Community Survey.
Weights were scaled to sum to the unweighted sample size of qualified veterans. Weights were then trimmed separately among post and pre-9/11 veterans.
General Population Adult Weight
For the general population weight, Ipsos started with the KnowledgePanel base weights and then raked to national demographic targets for the age 18+ population on the following variables computed from the Current Population Survey and the American Community Survey:
Weights were scaled to sum to the unweighted sample size of the general population adult respondents.
Precision of estimates
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 following table shows the unweighted sample sizes and the error attributable to sampling that would be expected at the 95% level of confidence for different groups in the survey:
Sample sizes and sampling errors for other subgroups are available upon request.
© Pew Research Center, 2019