The following describes the survey methodology of the 2018 Pre-Election Recontacts iteration of The Psychology Political Behavior Studies (PPBS). This report is meant to detail the utilized survey methodology and relevant, general purpose characteristics of both exploratory and confirmatory samples, as well as any extra samples and its combined version. The text is in APA Style and is akin to an APA-like ‘Methods Section’.

PPBS datasets are designed to have an exploratory, quota-based Nationally Representative sample (on Age, Education, Income and Sex), and a Confirmatory (Replication) convenience sample, from the same data source to avoid false positives. Some PPBS studies also have recontacts or extra-samples to answer additional specific research questions (e.g., 2nd Sample in 2016). All data’s coodbooks can be found at the bottom of the page, with a searchable feature allowing to find metadata within and between columns.

For more details, see PBBS’s Motivation.


Metadata of PBBS 2018 Pre-Election Samples
Sample 1 Sample 1-B
Election cycle Recontacts of Pre-Election 2018 [Standalone] Pre-Election 2018
Type Recontacts Convenience [Standalone] Convenience
Survey Period (Start) February 12th, 2019 February 12th, 2019
Survey Period (End) March 10th, 2019 March 10th, 2019
Country United States United States
Attention Checks Yes (13; various types) Yes (13; various types)
Time Checks Yes (11 page submit checks) Yes (11 page submit checks)
CAPTCHA Yes (begining of survey) Yes (begining of survey)
Sample Size (N) 609 622
Length of Interview (MD) 95.85 96.25
Attrition (%) 0.1 0.1
Data Quality checks (%) 0.09 0.09
Note. As explained more thoroughly below (last paragraph), Sample 1 and Sample 1-B are equal except for 13 cases.


Recontacts Sample (N=609)

Sample Description


In 2019, we re-hired Cint (www.cint.com), a survey research firm that recruits participants from a pool of over 13 million U.S. citizens, to recruit a recontacts sample of 609 Americans (68.64% women) from its panel who months prior had successfully completed the 2018 Psychology Political Behavior Studies (PPBS; from November 2nd to November 6th, 2018). The follow-up recontacts study took place in the first months of 2019 (from February 12 to March 10, 2019). The time difference between the two surveys ranged from 97 to 127 days (M = 102.81, SD = 4.83), or between a little over 3 months to a little over 4 months. All subjects in this sample participated successfully in both iterations of the PPBS (2018 Pre-Election and Pre-Election Recontacts).


In addition to administering a much greater number and variety of political and psychological instruments (including full scales) than in other nationally representative surveys (such as ANES, GSS, and WVS), we took a number of steps to insure that the quality of the data would be especially high. These included following professional recommendations to minimize problems of careless responding and satisficing behavior in online survey studies (Meade & Craig, 2012). Specifically, we employed 7 random attention questions, 5 page-time controls, and a Captcha Verification (or Completely Automated Public Turing Test to tell Computers and Humans Apart) question at the beginning of the survey.

We sent Cint a total of 3728 IDs from the 2018 Pre-Election studies, of which 775 participants were directed to the survey (16.34%), and 694 of them finished the survey (attrition rate 10%). There were 72 (9%) participants who failed more than two attention checks or time-checks, or finished the survey in under ~22 minutes and were therefore excluded. Lastly, thirteen participants were excluded from this sample because they had not successfully completed the initial study but successfully completed the recontacts phase. For the final sample of 609, participants who successfully completed all study materials had a completion time of 103.07 minutes on average (MD: 95.85min).

The age distribution of the sample was as follows: 18–24 years (0.99%), 25–34 (6.57%), 35–44 (13.96%), 45–54 (16.09%), 55–65 (29.72%), and older than 65 (32.68%). The ethnic breakdown was: White (88.83%), Black/African American (4.43%), Hispanic/Latino (2.46%), Asian/Pacific Islander (2.79%), Native American (0.16%), Middle Eastern (0%), and Other (1.31%). In terms of religion, (22% identified as Catholic, 45.48% as Protestant, 4.27% as Jewish,0.33% as Muslim, 13.96% as either Atheist or Agnostic, and 13.96% responded they are not sure or refused to answer. With respect to education, 2.79% declared their highest educational achievement to be less lower than high-school, 21.18% declared being High school graduates (including equivalencies), 35.63% indicated having Some college, no degree, and lastly, 40.39% indicated having received a Bachelor or Graduate degree. The median income category was $50,000 to $74,999. The exact distribution of Income is as follows: Less $15,000 (9.36%), $15,000 to $24,999 (11.66%), $25,000 to $34,999 (11.17%), $35,000 to $49,999 (16.42%), $50,000 to $74,999 (18.72%), $75,000 to $99,999 (15.44%), $100,000 to $149,999 (13.3%) and $150,000 more (3.94%).


Standalone Sample (N=622)

Sample Description

In 2019, we re-hired Cint (www.cint.com), a survey research firm that recruits participants from a pool of over 13 million U.S. citizens, to recruit a recontacts sample of 622 Americans (69.13% women) from its panel who months prior had successfully completed the 2018 Psychology Political Behavior Studies (PPBS; from February 12 to March 10, 2019). The follow-up recontacts study took place in the months after the 2018 US Midterms Election (from February 12 to March 10, 2019). The time difference between the two surveys ranged from 97 to 127 days (M = 102.81, SD = 4.83), or between a little over 3 months to a little over 4 months. All subjects in this sample participated successfully in both iterations of the The Psychology Political Behavior Studies (PPBS).

In addition to administering a much greater number and variety of political and psychological instruments (including full scales) than in other nationally representative surveys (such as ANES, GSS, and WVS), we took a number of steps to insure that the quality of the data would be especially high. These included following professional recommendations to minimize problems of careless responding and satisficing behavior in online survey studies (Meade & Craig, 2012). Specifically, we employed 7 random attention questions, 5 page-time controls, and a Captcha Verification (or Completely Automated Public Turing Test to tell Computers and Humans Apart) question at the beginning of the survey.

We sent Cint a total of 3728 IDs from the 2018 Pre-Election studies, of which 775 participants were directed to the survey (16.68%), and 694 of them finished the survey (attrition rate 10%). There were 72 (9%) participants who failed more than two attention checks or time-checks or finished the survey in under ~22 minutes and were therefore excluded. For the final sample of 622 participants who successfully completed all study materials had a completion time of 104.13 minutes on average (MD: 96.25min).

The sample distributions below mirror perfectly that of the recontacts samples because the Recontacts survey instrument did not ask the same demographic questions again. So the below demographic distributions refer to only 609 out of 622 participants.

The age distribution of our sample was as follows: 18–24 years (0.99%), 25–34 (6.57%), 35–44 (13.96%), 45–54 (16.09%), 55–65 (29.72%), and older than 65 (32.68%). The ethnic breakdown was: White (88.83%), Black/African American (4.43%), Hispanic/Latino (2.46%), Asian/Pacific Islander (2.79%), Native American (0.16%), Middle Eastern (0%), and Other (1.31%). In terms of religion, (22% identified as Catholic, 45.48% as Protestant, 4.27% as Jewish,0.33% as Muslim, 13.96% as either Atheist or Agnostic, and 13.96% responded they are not sure or refused to answer. With respect to education, 2.79% declared their highest educational achievement to be less lower than high-school, 21.18% declared being High school graduates (including equivalencies), 35.63% indicated having Some college, no degree, and lastly, 40.39% indicated having received a Bachelor or Graduate degree. The median income category was $50,000 to $74,999. The exact distribution of Income is as follows: Less $15,000 (9.36%), $15,000 to $24,999 (11.66%), $25,000 to $34,999 (11.17%), $35,000 to $49,999 (16.42%), $50,000 to $74,999 (18.72%), $75,000 to $99,999 (15.44%), $100,000 to $149,999 (13.3%) and $150,000 more (3.94%).

In sum, the difference between this Standalone sample (N=622) and the Recontacts sample (N=609) boils down to the 13 extra cases which have finished the Recontacts survey successfully but did not participate in the original PPBS Pre-election survey. We do not know how (or why) these participants arrived at the survey. Normally only the IDs we sent over should be invited but then again 13 out 3728 IDs (0.3%) is not a bad margin). Importantly, we didn’t exclude these 13 participants and present it as a ‘standalone’ sample because (a) these participants were paid for; (b) excluding or neglecting participants based on ‘convenience’ isn’t exactly methodologically sound; and (c) it may also be unethical to do so.






Codebook

Search box on the right finds items in all columns. Search boxes at the column level finds matches in their specific column.