Can AI Stand In for Human Survey-Takers? Not Really
Synthetic surveys using digital twins do a poor job estimating the public mood and are especially error-prone for some subgroups, including Republicans and Black adults.
Numbers, Facts and Trends Shaping Your World
Read our research on:
Methodological Research
Sign up for our Methods newsletter
The latest on survey methods, data science and more, delivered quarterly.
All
Methodological Research
Publications
-
What are nonprobability surveys?
Many online surveys are conducted using “nonprobability” or “opt-in” samples, which are generally easier and cheaper to conduct. In our latest Methods 101 video, we explore some of the features of nonprobability surveys and how they differ from traditional probability-based polls.
-
Methods 101: What are nonprobability surveys?
Our latest Methods 101 video explores some of the ways these surveys differ from traditional probability-based polls.
-
When writing about survey data, 51% might not mean a ‘majority’
For many people, “majority” is a word so common that they rarely have to think twice about what it means. But it’s a different matter for polling organizations like Pew Research Center. At the Center, writers cannot label a survey finding a “majority” unless it meets specific criteria.
-
Detecting subjectivity and tone with automated text analysis tools
There are a variety of tools that can help researchers analyze large volumes of written material. In this post, I’ll examine two of these…
-
Moderates in Congress go local on Facebook more than the most ideological members
For the average moderate legislator, about 54% of a member’s Facebook posts discussed local issues between 2015 and 2017. But for the average very liberal or very conservative legislator, just 38% of posts dealt with local issues.
-
How Does Pew Research Center Measure the Religious Composition of the U.S.? Answers to Frequently Asked Questions
Question 1: Measuring religious identity How does Pew Research Center measure the religious identity of survey respondents and the religious composition of the U.S.? Answer: Generally, we rely on respondents’ self-identification. A key question we ask in many surveys is: “What is your present religion, if any? Are you Protestant, Roman Catholic, Mormon, Orthodox such […]
-
Using APIs to collect website data
At Pew Research Center, we regularly use APIs to collect information for the studies we produce. Web APIs provide a means of communication between websites and users, structured by rules.
-
How to analyze Pew Research Center survey data in R
Pew Research Center releases its survey data publicly as IBM SPSS files with the .sav extension. But if you don’t have access to SPSS, there are free, open-source tools available to analyze and make use of the data.
-
Welcome to Decoded!
An introduction to the methodological musings, puzzles and tangles that you would see if you could flip those picture-perfect research products over.
-
The news that bots share on Twitter tends not to focus on politics
On Twitter, suspected bots are far more active in sharing links to news sites focusing on nonpolitical content than to sites with a political focus.
REfine Your Selection
Date
Years
Formats
Regions & Countries
Research Teams
Bylines
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.
Comparing Two Types of Online Survey Samples
Pew Research Center conducted a study to compare the accuracy of six online surveys of U.S. adults – three from probability-based panels and three from opt-in sources. On average, the absolute error on opt-in samples was about twice that of probability-based panels.
Q&A: What is the American Trends Panel, and how has it changed?
Members of the American Trends Panel can now take our surveys online or over the phone with an interviewer.
How Public Polling Has Changed in the 21st Century
A new study found that 61% of national pollsters used different methods in 2022 than in 2016. And last year, 17% of pollsters used multiple methods to sample or interview people – up from 2% in 2016.
