Sign up for our Methods newsletter
The latest on survey methods, data science and more, delivered quarterly
Research Methods
Confronting 2016 and 2020 Polling Limitations
Looking at final estimates of the outcome of the 2020 U.S. presidential race, 93% of national polls overstated the Democratic candidate’s support among voters, while nearly as many (88%) did so in 2016.
What 2020’s Election Poll Errors Tell Us About the Accuracy of Issue Polling
Given the errors in 2016 and 2020 election polling, how much should we trust polls that attempt to measure opinions on issues?
Measuring Religion in Pew Research Center’s American Trends Panel
Since the establishment of the ATP, the Center has gradually migrated away from telephone polling and toward online survey administration, and since early 2019, the Center has conducted most of its U.S. polling on the ATP. This shift has major implications for the way the Center measures trends in American religion – including those from the Center’s flagship Religious Landscape Studies, which were conducted by phone in 2007 and 2014.
Recent Publications
Q&A: After misses in 2016 and 2020, does polling need to be fixed again? What our survey experts say
Polling organizations have taken close looks at how election surveys are designed, administered and analyzed. We are no exception.
How we know the drop in Trump’s approval rating in January reflected a real shift in public opinion
The 9-point fall in approval was the largest change between two Pew Research Center polls since Donald Trump took office.
Understanding how 2020 election polls performed and what it might mean for other kinds of survey work
Many who follow polls are asking how these errors could happen. Here, we’ll take a preliminary shot at answering that question.
What we can trust 2020 election polls to tell us
Polls can't predict the future. But they are the best tool to reveal the public’s priorities and values, and why people vote the way they do.
A Resource for State Preelection Polling
If a battleground state poll does not adjust for having too many college graduates, it is at risk of overstating support for a Democratic presidential candidate. The Current Population Survey provides high-quality data that can mitigate overrepresentation of college graduates.
Key things to know about election polling in the United States
The real environment in which polls are conducted bears little resemblance to the idealized settings presented in textbooks.
What is machine learning, and how does it work?
Our latest Methods 101 video explains the basics of machine learning and how it allows our researchers to analyze data on a large scale.
Americans Give Higher Ratings to South Korea and Germany Than U.S. for Dealing With Coronavirus
U.S. adults give high marks to South Korea and Germany’s pandemic responses. In contrast, most believe China has done an only fair or poor job.
The coronavirus pandemic’s impact on Pew Research Center’s global polling
Our response to the pandemic has included the difficult decision to suspend much of our international survey work until further notice.
Assessing the Risks to Online Polls From Bogus Respondents
While the growth of online interviewing is a prominent trend in polling, there is variation within that trend in how researchers recruit respondents. This study finds that sourcing affects data quality.
Signature Reports
A Field Guide to Polling: Election 2020 Edition
While survey research in the United States is a year-round undertaking, the public’s focus on polling is never more intense than during the run-up to a presidential election.
Growing and Improving Pew Research Center’s American Trends Panel
Pew Research Center’s American Trends Panel (ATP) is now the Center’s principal source of data for U.S. public opinion research.
Comparing Survey Sampling Strategies: Random-Digit Dial vs. Voter Files
A new telephone survey experiment finds that an opinion poll drawn from a commercial voter file produces results similar to those from a sample based on random-digit dialing.
Are Telephone Polls Understating Support for Trump?
An experiment comparing responses to 27 questions fielded on both a telephone and a web survey found no significant mode differences in overall opinion about Trump or many of his signature policy positions.
Features
Methods 101 Video: How is polling done around the world?
Video: Can we still trust polls?
Methods 101 Video: Survey Question Wording
Methods 101 Video: Random Sampling
