Geographic Information System mapping as a tool to assess nonresponse bias in survey research

Oncologic PET/CT interpretation and reporting approaches

“…This survey was initiated in order to explore how imaging experts read and report oncologic FDG PET/CT studies. We used a web-based survey approach because this is an effective and technically feasible means of collecting data from busy health care professionals that provides valuable and reliable evaluations of professional practice patterns (11,19,23). The results of this survey should identify current shortcomings in image interpretation and reporting thereby providing useful information needed for the subsequent establishment of guidelines.…”

Using web demographics to model population change of Vietnamese-Americans in Texas between 2000 and 2009

“…Alternate methods include using an independent survey (Wright 2000), satellite imagery (Chen 2002), spatial analyses using Geographic Information System (GIS) (Hansen et al 2007), and spatial interpolation techniques (Lo 2008). While there has been a solid foundation in statistical research to adjust for non-response errors through sampling and statistical inferences (Wright 2000;Nirel and Glickman 2009), application of such techniques is not without legal controversies.…”

Is non-response contagious? The use of spatial information for predicting and weighting survey nonresponse

“…The basic idea of this contribution is quite simple: Given the often documented spatial clustering of survey nonresponse (e.g., N. Bates and Mulry, 2011;Biemer and Peytchev, 2013;Erdman and N. Bates, 2017;Hansen et al, 2007), we might wonder to which extent using the information about other units participation status, R j , in the vicinity of an observation i might improve the prediction of unit i's participation status, R i . Thus, we look for a model of the form…”

“…This spatial dependency has been recognized and researchers use, for example, geographic information systems (GIS) to map unit nonresponse in surveys and to identify areas with especially low participation rates in social surveys (Abbott and Compton, 2014;N. Bates and Mulry, 2011;Hansen et al, 2007). Related to this insight in the geographic correlates of survey nonresponse, researchers have turned to widely available aggregated measures to construct survey weights to minimize the impact of nonresponse bias, either by means of including aggregated measures and random eects when calculating inverse-probability weights or by means of calibration (Erdman and N. Bates, 2017;Kreuter, Olson, et al, 2010;Skinner and D'arrigo, 2011;Valliant, Dever, and Kreuter, 2018).…”