Suchergebnisse

"Falling response rates and the advancement of technology have shaped the discussion in survey methodology in the last few years. Both led to a notable change in data collection efforts. Survey organizations try to create adaptive recruitment and survey designs and increased the collection of non-survey data for sampled cases. While the first strategy is an attempt to increase response rates and to save cost, the latter is part of efforts to reduce possible bias and response burden of those interviewed. To successfully implement adaptive designs and alternative data collection efforts researchers need to understand error properties of mixedmode
and multiple-frame surveys. Randomized experiments might be needed to gain that knowledge. In addition close collaboration between survey organizations and researchers is needed, including the possibility and willingness to shared data between those organizations. Expanding options for graduate and post-graduate education in survey methodology might help to increase the possibility for high quality surveys." [author's abstract]

Solutions to common problems in preelection surveys are described using the Gallup Poll as an example. A history of sampling theory is given, & examined are problems in & solutions to: (1) sampling, (2) estimation, (3) response validity, (4) the undecided, (5) measuring the likelihood to vote, & (6) measuring late trends in voter preference. Cited are demonstrable gains in accuracy that have followed application of the described solutions. 1 Table. Modified HA.