American Trends Panel Wave 18
DOI
10.17605/OSF.IO/PKWC5Summary
The American Trends Panel (ATP) is a national, probability-based online panel of adults in the United States living in households. Adults who use the Internet participate in the panel via self-administered web surveys, and adults who do not use the Internet participate via mail. The 18th wave of the panel survey was fielded for the Pew Research Center by Abt SRBI from June 7 to July 5, 2016. In total, 4,602 ATP members completed the survey, with 4,172 participating by web and 430 participating by mail. The survey was administered in English and Spanish. Survey weights are provided to account for differential probabilities of selection into the panel as well as differential nonresponse to the panel recruitment survey, the panel invitation, and the panel survey itself (Wave 18). The margin of sampling error for full sample weighted estimates is +/- 2.28 percentage points. The ATP Wave 18 asked questions about politics pre-election, U.S. political items, journalism, and religion items.The ARDA has added six additional variables to the original data set to enhance the users' experience on our site.
Data File
Cases: 4602Variables: 185
Weight Variable: WEIGHT_W18
WEIGHT_W18 is the weight for the combined sample of all web and mail interviews. Data for all Pew Research Center reports are analyzed using this weight.
Data Collection
June 7, 2016-July 5, 2016Original Survey (Instrument)
Wave 18 American Trends PanelFunded By
Pew Research CenterCollection Procedures
Currently all ATP panelists have been recruited from two large (n=10,013 and n=6,004) national overlapping dual frame landline and cell phone random digit dial (RDD) surveys conducted for the Pew Research Center. At the end of each RDD survey, respondents were invited to join the panel. The first RDD survey was conducted from January 23 to March 16, 2014, and the second RDD survey was conducted from Aug. 27 to Oct. 4, 2015, both in English and Spanish. Sample for the RDD surveys was obtained from SSI. Please refer to the Pew Research Center Political Typology/Polarization Survey Methodology Report and 2015 Pew Governance Survey Methodology Report for additional information on the sample design for the RDD surveys.ATP panelists who reported using the Internet and for whom we had an email address were invited to participate in Wave 18 via a self-administered web survey. The data collection for the web survey was conducted from June 13 to July 5, 2016. Advance postcards were mailed to all web mode panelists with a known residential address. One-hundred panelists were included in a soft launch of the web survey, which began with an initial email invitation sent on June 13, 2016. The web panelists chosen for the soft launch were known responders to previous ATP surveys who had completed their surveys within two days of receiving their invitation. The remaining panelists assigned to the web mode were included in the full launch and were sent an initial email invitation on June 14. All web mode panelists who previously provided consent to receive text messages received a text message invitation in addition to their email invitation. Panelists who were known to have short codes blocked from previous survey wave SMS invitations were not included in this group. A total of 1,852 SMS invitations were sent. Up to four reminder emails and SMS messages were sent to those who did not respond to the web survey. The web survey was closed July 5, 2016 at 9 a.m. Eastern.
ATP web panelists who completed their survey in Spanish were offered a $20 post-paid incentive for completing the Wave 18 web survey. Panelists who were age 18-25, African American, with high school education or less, were not registered to vote or reported being Hispanic but taking the survey in English in the RDD recruitment survey were offered a $10 post-paid incentive for completing the Wave 17 web survey. All other panelists who completed the web survey were offered a $5 post-paid incentive. web respondents could choose to receive the post-paid incentive in form of a check or a gift code to Amazon.com. The differential incentive amounts were designed to increase panel survey participation among groups that traditionally have low survey response propensities.
At the start of the Wave 18 Survey, 574 ATP members belonged to the non-Internet arm of the panel. The data collection for both English and Spanish language mail surveys was conducted June 7 to June 27, 2016 following the timeline shown in Table 2. The first packet of English language surveys was mailed using first class mail and Spanish language surveys were mailed using Priority Mail. ATP mail panelists were offered a cash pre-incentive that was included in their first survey packet. The same differential amounts that web panelists received were also used for mail panelists. A reminder postcard was sent to all mail mode respondents. The second survey packet was mailed to 340 mail mode respondents who did not have a survey returned by June 17, 2016. The cutoff date to process returned mail surveys was June 27, 2016 which allowed a week for final data entry and quality checking.
Wave 18 is the first wave where a subset of the non-Internet panelists was converted to web mode. A pilot test of the conversion effort was conducted starting on April 11, 2016 and continued through Wave 18. The pilot conversion process involved calling 100 mail mode respondents and asking them to report their Internet and device status and then asking them to convert to web. For those who already had the means for taking web surveys, they were simply asked to convert (15 such panelists agreed to convert). For those without the means for taking web surveys (no device and/or Internet access), they were offered an Internet-connected tablet computer at no cost to the panelist. Tablets were shipped to the panelists who accepted (49 such panelists agreed to convert) and they were given a follow-up call to ensure they understood how to use the tablet to access American Trends Panel surveys through a pre-installed Mobile Panel App. A total of 20 Pilot panelists refused to convert and 19 had not yet been contacted at the time of this report. A total of 38 Pilot cases were then moved from Mail to web mode in Wave 18, and 24 of them (74%) completed Wave 18 via the web.
