Two papers published in the Journal of Survey Statistics and Methodology will be featured in invited sessions at the Joint Statistical Meetings in Seattle this August.
The first, “Accuracy in Estimation with Nonresponse: A Function of Degree of Imbalance and Degree of Explanation,” is by Carl-Erik Sarndal and Peter Lundquist. With ever-higher levels of nonresponse, researchers have tried to use “responsive” designs with the objective of realizing a well-balanced final set of respondents. This means monitoring the composition of the sample using auxiliary variables. Auxiliary variables are important at the estimation stage as well (e.g., when calibrated weights are used in the nonresponse adjustment). The main questions addressed in this talk are the following: Is balancing worth a perhaps costly and demanding effort in data collection? Could one have done equally well by saving the use of the auxiliary information for the estimation stage?
The second paper is “Representative Surveys in Insecure Environments: A Case Study of Mogadishu, Somalia,” by Jesse Driscoll and Nicholai Lidow. This talk will describe the first representative survey conducted in 25 years in Mogadishu, including the challenges related to the lack of data for constructing a frame, poor security, and the fragmented nature of authority within the city. The key elements in this successful effort were the use of remote sensing, the systematic development of local contacts through the Somali diaspora, the flexible deployment of staff, and mobile technology. Given the importance of reliable estimates for humanitarian response and policy choices, documenting the shortcomings and lessons learned are important for future data-collection efforts in insecure environments.
The Journal of Survey Statistics and Methodology is cosponsored by the American Statistical Association and American Association for Public Opinion Research.
Leave a Reply