Suchergebnisse

The rise of the Internet has radically altered survey research by changing how we think about sampling, driving down the cost of interviewing, and creating new ways of asking questions. This technology has also opened the way to a new style of cooperatively organized survey research. Projects such as the Cooperative Congressional Election Study (CCES) and the Cooperative Campaign Analysis Project (CCAP) involve collaborations of dozens of research teams that can collect very large samples and many smaller surveys tailored to the research questions of particular teams. This review examines the organization and key findings of these projects as well as their sampling methodology and its validity. Of particular importance, this article offers a direct comparison of the CCES with actual election results and the American National Election Studies (ANES), showing that the new survey approach yields highly accurate results that replicate the correlation structure of the ANES.

The rise of the Internet has radically altered survey research by changing how we think about sampling, driving down the cost of interviewing, and creating new ways of asking questions. This technology has also opened the way to a new style of cooperatively organized survey research. Projects such as the Cooperative Congressional Election Study (CCES) and the Cooperative Campaign Analysis Project (CCAP) involve collaborations of dozens of research teams that can collect very large samples and many smaller surveys tailored to the research questions of particular teams. This review examines the organization and key findings of these projects as well as their sampling methodology and its validity. Of particular importance, this article offers a direct comparison of the CCES with actual election results and the American National Election Studies (ANES), showing that the new survey approach yields highly accurate results that replicate the correlation structure of the ANES. Adapted from the source document.

Missing data are common in observational studies due to self-selection of subjects. Missing data can bias estimates of linear regression and related models. The nature of selection bias and econometric methods for correcting it are described. The econometric approach relies upon a specification of the selection mechanism. We extend this approach to binary logit and probit models and provide a simple test for selection bias in these models. An analysis of candidate preference in the 1984 U.S. presidential election illustrates the technique.