"Addressing missingness using two-phase sampling for nonresponse: methods and benefits"
Add to your list(s)
Download to your calendar using vCal
If you have a question about this talk, please contact Alison Quenault.
Nonresponse is common in epidemiological surveys and clinical trials. Common methods for dealing with missing data rely on untestable assumptions. Nonresponse two-phase sampling (NTS), which re-contacts and collects data from a subsample of the initial nonrespondents, has been used to reduce nonresponse bias. We propose two methods for dealing with data collected from NTS sampling: (1) Nonrespondent subsample multiple imputation (NSMI), where multiple imputation was performed within the subsample of nonrespondents in phase I using additional data collected in phase II; (2) A Bayesian selection model which utilizes the additional data collected in phase II of data collection. We examine the performance of the methods under various missing data mechanisms using simulation studies and apply the methods to a Quality of Life (QOL) dataset. The simulation study shows that the gain of using the NTS scheme can be substantial, even if NTS sampling only collects data from a small proportion of the initial nonrespondents.
This talk is part of the MRC Biostatistics Unit Seminars series.
This talk is included in these lists:
Note that ex-directory lists are not shown.
|