Optimal design when outcome values are not missing at random

DOI10.5705/SS.202016.0526MaRDI QIDQ4558444zbMATH OpenOpenAlexFDO

Authors Kim May Lee, Robin Mitra, Stefanie Biedermann

Publication date 22 November 2018

Published in STATISTICA SINICA (Search for Journal in Brave)

Full work available at URL http://oro.open.ac.uk/72258/1/A28n48.pdf

zbMATH Keywords

covariance matrixinformation matrixlinear regression modelmissing observationsnot missing at randomoptimal design

Mathematics Subject Classification ID

Linear regression; mixed models (62J05) Optimal statistical designs (62K05)

Recommendations

• Optimal design for experiments with possibly incomplete observations
• Robust optimal design when missing data happen at random
• Optimal design of experiments with anticipated pattern of missing observations
• Robustness of classical and optimal designs to missing observations
• Factorial and response surface designs robust to missing observations

Cited in

(6)

• Optimal design for experiments with possibly incomplete observations
• Comparison of listwise deletion and imputation methods for handling a single missing response value in a central composite design
• Response-adaptive randomization in clinical trials: from myths to practical considerations
• To add or not to add a new treatment arm to a multiarm study: a decision-theoretic framework
• D-optimal designs for multiarm trials with dropouts
• Optimal designs for logistic mixed models with dropouts

This page was built for publication: Optimal design when outcome values are not missing at random

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q4558444)