A number of people contributed to this report. Amy Mitchell, director of journalism research, oversaw the research project and served as lead author of the report. Senior Researcher Jocelyn Kiley led the development of the survey instrument and methodological strategy. Kiley, Research Associate Jeffrey Gottfried and Research Analyst Emily Guskin managed the data and analysis.

The report was written by Mitchell, Gottfried, Guskin and Senior Researcher Jesse Holcomb. Research Analyst Katerina Matsa developed the charts and graphs. The report was number checked by Gottfried, Guskin, Kiley and Matsa and copy edited by Communications Associate Molly Rohal.

Director of Survey Research Scott Keeter provided research and editorial guidance. Communications Manager Dana Page handled outreach for the project and Google Journalism Fellow Jan Boyles provided assistance in the development of the questionnaire. Research Assistant Seth Motel assisted with data management. Jessica Schillinger created graphics for the report.

The analysis in this report is based on a survey conducted Aug. 21-Sept. 2, 2013, among a sample of 5,173 adults 18 years of age or older. The survey was conducted by GfK among a random sample of households in their nationally representative online research panel, KnowledgePanel. GfK panel members are recruited through probability sampling methods and include both those with internet access and those without (GfK provides internet access for those who do not have it and, if needed, a device to access the internet when they join the panel). A combination of random digit dialing (RDD) and address-based sampling (ABS) methodologies have been used to recruit panel members (in 2009 GfK switched their sampling methodology for recruiting panel members from RDD to ABS). The panel includes households with landlines and cellphones, including those only with cellphones, and those without a phone. Both the RDD and ABS samples were provided by Marketing Systems Groups (MSG). GfK continually recruits new panel members throughout the year to offset panel attrition as people leave the panel. The survey was conducted in English.

Respondents were selected randomly from eligible adult household members of the panel. Of the 5,173 adults in the full sample who completed the survey, 64% were identified as Facebook users, and 30% were identified as Facebook news consumers. All sampled members received an initial email to notify them of the survey and provide a link to the survey questionnaire. Additional follow-up reminders were sent as needed to those who had not yet responded.

The final sample of 5,173 adults was weighted using an iterative technique that matches gender, age, race/ethnicity, education, region, household income, home ownership status and metropolitan area to parameters from the July 2013 Census Bureau’s Current Population Survey (CPS). In addition, the sample is weighted to match current patterns of internet access from the July 2011 CPS survey. This weight is multiplied by an initial sampling or base weight that corrects for differences in the probability of selection of various segments of GfK’s sample and by a panel weight that adjusts for any biases due to nonresponse and noncoverage at the panel recruitment stage (using all of the parameters described above). Details about the GfK panel-level weights can be found at:

http://marketing.gfkamerica.com/knowledgenetworks/knpanel/docs/KnowledgePanel(R)-Design-Summary-Description.pdf 

Sampling errors and statistical tests of significance take into account the effect of weighting at each of these stages. The margin of sampling error at the 95% confidence level is plus or minus 1.7 percentage points for results based on the full sample (n=5,173). The margin of sampling error is plus or minus 2.2 percentage points for Facebook users (n=3,268) and plus or minus 3.3 percentage points for Facebook news consumers (n=1,429). Sample sizes and sampling errors for other subgroups are available upon request.

In addition to sampling error, one should bear in mind that question wording and practical difficulties in conducting surveys can introduce error or bias into the findings of opinion polls.