The Pew Research Center conducted Wave 191 of the American Trends Panel survey on religious service attendance from April 6–12, 2026. The survey included 3,592 respondents out of 3,775 sampled, yielding a survey-level response rate of 95%.
SSRS administered the survey for Pew Research Center using both online (n=3,491) and live telephone (n=101) interviewing methods. Interviews were conducted in English and Spanish. Online panelists received an email invitation and up to two email reminders if they did not initially respond. Those who consented to SMS messages also received a text message with a survey link and up to two SMS reminders. Phone panelists were contacted through up to six calls by trained SSRS interviewers, and prenotification postcards were mailed to them on April 3.
The survey launched in two phases: a soft launch on April 6 with 60 online panelists and five completed phone interviews, followed by a full launch on April 7 for all remaining eligible online panelists. The overall target population consisted of noninstitutionalized U.S. adults aged 18 and older. Within each sampled household, the adult with the next birthday was selected to participate.
The final dataset excluded three respondents due to patterns of satisficing prior to weighting and analysis. The cumulative response rate—accounting for nonresponse to recruitment surveys and panel attrition—was 3%. Among those who logged on and completed at least one survey item, the break-off rate was less than 1%.
The findings reported are based on 1,391 respondents who said they attend religious services at least once or twice a month. The margin of sampling error for this subgroup is plus or minus 3.5 percentage points. The survey included oversamples of non-Hispanic Asian adults, White evangelical Protestants, White nonevangelical Protestants, Black Protestants, and Catholics—all of whom attend services monthly. These oversampled groups were later weighted to reflect their proper proportions in the general population.
Respondents received a post-paid incentive of $5 to $15, depending on how difficult they were to reach, and could choose between a check or a gift code for Amazon.com, Target.com, or Walmart.com. Since 2018, the American Trends Panel has used address-based sampling for recruitment, drawing from the U.S. Postal Service’s Computerized Delivery Sequence File, which covers an estimated 90% to 98% of the population. The panel has recruited a national sample of U.S. adults approximately once per year since 2014. ATP data undergoes a multi-stage weighting process that adjusts for sampling design and nonresponse, with respondent weights trimmed at the 1st and 99th percentiles to minimize precision loss.