Using proxy measures and other correlates of survey outcomes to adjust for non‐response: examples from multiple surveys

By Frauke Kreuter, Kristen Olson, J. Wagner, Ting Yan, T. Ezzati-Rice, Carolina Casas-Cordero, Michael LeMay, Andy Peytchev, R. Groves, Trivellore E. Raghunathan. 2010

158 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Estimation of an indicator of the representativeness of survey response (2012, background): “An Rindicator cannot be viewed separately from the auxi liary vector X that was used to define it. As such, indicator values should always be reported with reference to the auxiliary variables. Consequently, when comparing m ultiple surveys within one survey institute, over survey institutes or even”
Summary Report of the AAPOR Task Force on Non-probability Sampling (2013, background): “Research to date on the effectiveness of webographic questions and paradata for propensity modeling is mixed (Schonlau, van Soest, and Kapteyn 2007; Kreuter et al. 2011).”
Consequences of Survey Nonresponse (2013, background): “To date, these data have shown limited promise for nonresponse adjustment (Kreuter et al. 2010).”
Proxy Pattern-Mixture Analysis for Survey Nonresponse (2011, background): “2) correlations with outcomes (Kreuter et al. 2010), while for item nonresponse we would expect higher correlations.”
Unit Nonresponse and Weighting Adjustments: A Critical Review (2013, background): “The use of paradata is a rapidly developing area, but initial findings reveal that this may be a difficult task (Kreuter et al. 2010).”