Using Calibration Weighting to Adjust for Nonresponse and Coverage Errors

By Phillip S. Kott. 2006

227 citations recorded by the source corpus.

View Paper: https://www.semanticscholar.org/paper/f58d7ff4248ae4e42560f38a12d03df53e4e81f2

How researchers see this paper

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

1. Shu Yang
2. Sixia Chen
3. Ted Chang
4. R. Valliant
5. Sunghee Lee
6. Phillip S. Kott
7. Jae Kwang Kim
8. Yilin Chen

Citations in the corpus

• Propensity Score Weighting for Causal Inference with Clustered Data (2017, methodology): “In survey sampling, calibration is widely used to integrate auxiliary information in esti- mation or handle nonresponse; see, e.g., Wu and Sitter (2001), Chen et al. (2002), Kott (2006), Chang and Kott (2008) and Kim et al. (2016).”
• Using Calibration Weighting to Adjust for Nonresponse Under a Plausible Model (with full appendices) (2007, methodology): “In Kott (2006) that is no longer the case, so model-covariates totals need not be known.”
• Calibration Estimation in Survey Sampling (2010, unknown): “The IV calibration estimator has been discussed in Estevao and S¨arndal (2000, 2006) and Kott (2003).”
• Multiply robust imputation procedures for the treatment of item nonresponse in surveys (2017, methodology): “In the context of survey data, doubly robust procedures have been discussed in Kott (1994), Kott (2006), Kim & Park (2006), Haziza & Rao (2006), Kott & Chang (2010), Haziza et al. (2014), and Kim & Haziza (2014), among others.”
• Estimation for Volunteer Panel Web Surveys Using Propensity Score Adjustment and Calibration Adjustment (2009, background): “Calibration can reduce variances and can also correct for both nonresponse and coverage errors that are not handled by the propensity adjustments in the previous section (e.g., see Kim, Li, and Valliant 2007; Kott 2006).”
• Using Calibration Weighting to Adjust for Nonignorable Unit Nonresponse (2010, methodology): “As shown in Kott (2006), under certain conditions, an asymptotically unbiased estimator for both the (conditional) prediction-model variance and quasi-randomization mean squared error of t̂yz,h (under the respective models) would be v̂ = ∑ k∈S (w2k − wk)e2k, (11) where ek = yk − xTk {∑ j∈S djh1(zTj…”