My da|ra Login

Detailed view

metadata language: English

Web data collection across devices: smartphone, tablet, and PC. 2015

Resource Type
Dataset : survey data
  • Tourangeau, Roger (Westat)
Publication Date
Funding Reference
  • National Science Foundation
    • Award Number: SES-1261340
  • Abstract

    Under a grant from the National Science Foundation (NSF), Westat conducted an evaluation of how different data collection devices affect data quality, usability, respondent acceptance, and response behaviors for sensitive questions. This evaluation was unique in that sampled respondents were assigned to a device type for completing the survey. Devices included a laptop PC, tablet, or smartphone.

    Westat conducted more than 500 in-person interviews across eight primary sampling units (PSUs) using an address-based sample (ABS). Respondents were randomly assigned to one of the three device types within each PSU. Westat developed the web questionnaire, which was accessible only by the assigned device type, and trained field interviewers on the experimental design and procedures. Westat also provided respondents with the assigned device type and mobile web access. Interviewers had MiFi devices that could connect to the Internet across a cellphone network.

    The web questionnaire included several experiments to test the effect of visibility as a function of screen size and to examine the potential of mobile devices for collecting sensitive information. The results will inform and guide the understanding of how survey data collection is being affected by technological changes and how respondents use these devices to access surveys. Deliverables included a number of peer-reviewed publications.
  • Technical Information

    Response Rates: A total of 512 interviews were completed, for an overall response rate (AAPOR RR3) of 30.4 percent. The response rates did not differ significantly across the three device conditions (smartphone 32.9 percent, tablet 29.6 percent, and laptop 28.8 percent). Only two cases could not be completed because of problems with cellular coverage (one each in the smartphone and laptop conditions).
Temporal Coverage
  • 2015-01-21 / 2015-05-04
    Time Period: Wed Jan 21 00:00:00 EST 2015--Mon May 04 00:00:00 EDT 2015 (Winter-Spring 2015)
  • 2015-01-21 / 2015-05-04
    Collection Date(s): Wed Jan 21 00:00:00 EST 2015--Mon May 04 00:00:00 EDT 2015 (Winter-Spring 2015)
Geographic Coverage
  • Continental United States
Sampled Universe
Adults age 18 or olderSmallest Geographic Unit: PSU
We selected address-based samples in each of eight counties around the United States.  The counties were selected purposively, based on the availability of experienced field staff there.  Still, the set of eight sample counties encompassed a range of different types of areas.  Seven were in metropolitan statistical areas and the other was rural; one of the seven metropolitan areas involved a small central city.  The eight counties included all four Census regions.  Within each county, we selected a full probability sample of addresses.  We used Census block groups as the second-stage sampling units (SSUs).  Six SSUs were selected from each county with probabilities proportional to size (in housing units).  One SSU was on a military base and was replaced with the next SSU in the county.  In total, we selected 1,824 addresses, 228 within each sample county and 38 in each sample SSU.  One hundred forty-two of the addresses were vacant, could not be found, or turned out not to be dwellings, leaving a final sample of 1,682 occupied dwelling units.  When they contacted a household, interviewers tried to complete a short screener with an adult there.  In households with just one adult, he or she was selected for the main interview; in households with two adults, one of the two was selected randomly; and, in households with three or more adults, the last birthday method was used to select one for the main interview.  Once the sample person had been designated, he or she was asked to complete the interview on a device that had been randomly determined ahead of time.  Sample persons were offered a $20 incentive to complete the questionnaire.
Collection Mode
  • web-based survey~~


Update Metadata: 2018-12-13 | Issue Number: 1 | Registration Date: 2018-12-13

Tourangeau, Roger (2018): Web data collection across devices: smartphone, tablet, and PC. 2015. Version: 1. ICPSR - Interuniversity Consortium for Political and Social Research. Dataset.