Abstract
Missing data in clinical trials are defined as planned information that was not collected. Examples of these include a subject withdrawing consent before the end of a trial or a laboratory test that cannot be obtained. Depending on why and how much data are missing, the results and interpretability of the trial can be jeopardized. Fortunately, there is a vast literature about statistical methods that can handle missing data. Probably the most important—and least technical—point in this literature is to do everything possible beginning at the trial design stage to avoid missing data. Even when the trial is designed to minimize missing data, the analysis plan should address how the analysis will proceed in the presence of missing data. This chapter should be viewed as a springboard into understanding the minimal amount of theory to apply these methods and begin reading the source literature.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Notes
- 1.
The model can be extended further by allowing R to take on more than two values indicating multiple response patterns. This will be necessary for applying pattern mixture models.
- 2.
Common notation for the Var(e) is R but has been changed to P to avoid confusion with the response vector R.
References
Cao, W., Tsiatis, A. A., & Davidian, M. (2009). Improving efficiency and robustness of the doubly robust estimator for a population mean with incomplete data. Biometrika (Oxford Academic).
Carpenter, J., & Kenward, M. (2012). Multiple imputation and its application. Statistics in Practice. Wiley.
Collins, L. M., Schafer, J. L., & Kam, C.-M. (2001). A comparison of inclusive and restrictive strategies in modern missing data procedures. Psychological Methods, 6(4), 330–351.
Fairclough, D. L. (2010). Design and analysis of quality of life studies in clinical trials, 2nd ed. Chapman and Hall/CRC.
Ibrahim, J.G., & Molenberghs, G. (2009). Missing data methods in longitudinal studies: A review. Test, 18(1), 1–43.
Kang, J. D. Y., & Schafer, L. J. (2007). Demystifying double robustness: A comparison of alternative strategies for estimating a population mean from incomplete data. Statistical Science, 22(4), 523–539.
Mallinckrodt, C. H., Scott Clark, W., & David, S. R. (2001). Type i error rates from mixed effects model repeated measures versus fixed effects ANOVA with missing values imputed via last observation carried forward. Drug Information Journal, 35(4), 1215–1225. https://doi.org/10.1177/009286150103500418
Mallinckrodt, C. H., Lin, Q., Lipkovich, I., & Molenberghs, G. (2012). A structured approach to choosing estimands and estimators in longitudinal clinical trials. Pharmaceutical Statistics, 11(6), 456–461.
Molenberghs, G., & Verbeke, G. (2005). Models for discrete longitudinal data. Springer.
National Research Council (2010). The Prevention and Treatment of Missing Data in Clinical Trials.
O’Neill, R. T., & Temple, R. (2012). The prevention and treatment of missing data in clinical trials: An FDA perspective on the importance of dealing with it. Clinical Pharmacology and Therapeutics, 91(3), 550–554.
Rubin, D. B. (1996). Multiple imputation after 18 years. Journal of the American Statistical Association, 91(434), 473.
SAS/STAT 14.1 user’s guide, Carey, NC (2015).
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2018 Springer Nature Singapore Pte Ltd.
About this chapter
Cite this chapter
Gilbert, S.A., Christensen, J.C. (2018). Missing Data. In: Peace, K., Chen, DG., Menon, S. (eds) Biopharmaceutical Applied Statistics Symposium . ICSA Book Series in Statistics. Springer, Singapore. https://doi.org/10.1007/978-981-10-7826-2_9
Download citation
DOI: https://doi.org/10.1007/978-981-10-7826-2_9
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-10-7825-5
Online ISBN: 978-981-10-7826-2
eBook Packages: Mathematics and StatisticsMathematics and Statistics (R0)