Kaiser Family Foundation/New York Times/CBS News Non-Employed Poll

The Kaiser Family Foundation/New York Times/CBS News Non-Employed Poll is based on telephone interviews conducted November 11 through November 25 with 1,002 respondents between the ages of 25 and 54 who are currently not employed either full-time or part-time.  Interviews were administered in English and Spanish, combining random samples of both landline and cellular telephones.

The Foundation, The Times, and CBS News contributed financing for the survey, and teams from all three organizations worked together to develop the questionnaire and analyze the data. Each organization is solely responsible for its content.

SSRS of Media, Pennsylvania conducted sampling, interviewing, and tabulation for the survey. Respondents were reached in one of three ways:

1. 350 interviews were completed with respondents reached through random-digit dialing to landline (N=151) and cell phones (N=199) specifically for the Non-Employed Poll;
2. 157 interviews were completed with respondents reached via landline (N=78) and cell phone (N=79) as part of the weekly SSRS omnibus poll, which also utilizes random digit dialing to reach respondents;
3. 495 interviews (261 landline and 199 cell phone) were completed by dialing numbers where interviews had been recently completed as part of the SSRS omnibus poll and respondents’ previous answers indicated they met inclusion criteria for the survey.

For each sample, landline telephone exchanges were randomly selected from a complete list of active phone exchanges. The samples were designed so that the selected exchanges amounted to a proportional geographic representation of the U.S. (including Alaska and Hawaii). Within each exchange, random digits were added to form complete telephone numbers.  Cellular telephone numbers were generated using a similar procedure to the one described for landlines. Both the landline and cell phone samples were generated by  Marketing Systems Group. Within each household reached by landline, one qualifying adult was designated by a random procedure to be the respondent for the survey. Cell phone interviews were completed with the qualifying adult answering the phone.

Interviewers made multiple attempts to reach every phone number in the survey, calling back unanswered numbers on different days at different times of both day and evening, and attempting to convert initial refusals.

The combined results have been weighted to adjust for the fact that not all survey respondents were selected with the same probability, to address the implications of sample design, and to account for systematic nonresponse along known population parameters. The first weighting stage was conducted separately for each of the 3 samples, and addressed differences in probability of selection stemming from respondents’ likelihood of owning multiple telephones, as well as the number of adults in each household. The callback sample was also adjusted for individual propensity to respond to a follow-up contact.

In the second weighting stage, the 3 samples were combined and adjusted to match known demographic distributions of the target population. Typically, researchers use demographic weighting parameters based on national administrative data sources such as the U.S. Census Bureau’s American Community Survey. However, the non-employed as defined for this poll are not equivalently captured by the Census Bureau employment definitions. Thus, to generate population parameters, SSRS calculated population weights for all interviews completed to date in 2014 on its omnibus poll with respondents 25 to 54 years old (N=19,269) by matching estimates from the Census Bureau’s Current Population Survey March 2014 Supplement based on age, gender, race/ethnicity, nativity (for Hispanics), education, marital status, Census region, and phone status. These interviews were then filtered to only include those ages 25 to 54 who are non-working (N=4,574). This created population parameters unique to the target population, which were used as targets for demographic weighting of the combined sample. Self-defined employment status (homemaker, student, retired, temporarily unemployed, other) was also added as a weighting target in the final stage.

The margin of sampling error including the design effect for the full sample is plus or minus 4 percentage points. Numbers of respondents and margin of sampling error for key subgroups are shown in the table below. For results based on other subgroups, the margin of sampling error may be higher. Sample sizes and margins of sampling error for other subgroups are available by request. Note that sampling error is only one of many potential sources of error in this or any other public opinion poll.

Kaiser Family Foundation public opinion and survey research is a charter member of the Transparency Initiative of the American Association for Public Opinion Research.