Fact TankJune 16, 2016

In the age of big data, survey research will not only survive but thrive

The next frontier of public-opinion research is already visible in the “big data” revolution. Through the digital traces of our everyday activities, we are creating a massive volume of information that can tell us a lot about ourselves. Smart data science can identify patterns in our behaviors and interests. And in some domains, such as […]

MethodsMay 11, 2016

The challenges of polling Asian Americans

Why aren’t Asian Americans shown as a separate group when differences among whites, blacks and Hispanics are discussed in survey reports? It’s a good question, so we put together a summary of some of the methodological and other issues on accurately polling U.S. Asians.

MethodsMay 2, 2016

What we learned about online nonprobability polls

The advantages of these online surveys are obvious – they are fast and relatively inexpensive, and the technology for them is pervasive. But are they accurate?

Pew Research CenterJanuary 7, 2016

Appendix C: Sensitivity to the turnout forecast

The candidate preferences of voters and nonvoters in 2014 were very different. This fact makes cutoff methods very sensitive to the chosen turnout threshold. Using the Perry-Gallup method, the forecast margin ranges from a tie vote (47%-47%) with a more inclusive model (a turnout forecast of 60% of registered voters, 42% of the general public) […]

Pew Research CenterJanuary 7, 2016

Appendix B: The choice of a turnout measure

There are two indicators of voter turnout available for the type of analysis in this report: (1) each respondent’s self-report in the post-election survey and (2) a voter file record of turnout. Among registered voters, 63% have a voter file record indicating that they voted in 2014 (“verified voters”) and 75% said they voted (“self-reported […]

Pew Research CenterJanuary 7, 2016

Appendix A: The Perry-Gallup measures

The items used in the so-called Perry-Gallup scale – originally developed in the 1950s and ’60s by election polling pioneer Paul Perry of Gallup and used in various combinations and with some alterations by the Pew Research Center, Gallup and other organizations in their pre-election polling (Perry 1960, 1979) – are widely employed by survey […]

Pew Research CenterJanuary 7, 2016

Methodology

The American Trends Panel surveys (ATP) The American Trends Panel (ATP), created by Pew Research Center, is a nationally representative panel of randomly selected U.S. adults living in households. Respondents who self-identify as internet users (representing 89% of U.S. adults) participate in the panel via monthly self-administered Web surveys, and those who do not use […]

Pew Research CenterJanuary 7, 2016

Acknowledgements

This report is a collaborative effort based on the input and analysis of the following individuals: Primary Researchers Scott Keeter, Senior Survey Advisor Ruth Igielnik, Research Associate Andrew Mercer, Research Methodologist Jocelyn Kiley, Associate Director, Research Collaborating Researchers Claudia Deane, Vice President, Research Michael Dimock, President Ken Goldstein, University of San Francisco Courtney Kennedy, Director […]

Pew Research CenterJanuary 7, 2016

4. Conclusion

The analysis presented here suggests that modeling the electorate is likely to continue to vex pollsters, especially if no official record of past voting is available as an input to the models. As if to affirm this somewhat pessimistic conclusion, polls have failed to accurately predict winning candidates in several recent elections, including the 2015 […]

Pew Research CenterJanuary 7, 2016

3. Comparing the results of different likely voter models

All told, we tested 16 different variations on four types of likely voter methods, producing estimates that range from a 2-point Democratic lead to a 7-point Republican advantage in the generic U.S. House vote. The benchmark for comparison is a 3-point Republican lead among verified voters (49% Republican, 46% Democratic) when they were interviewed prior […]