Missing responses in adaptive allocation design
AbstractAdaptive allocation designs are used in phase III clinical trials. Sometimes, from ethical considerations, the goal may be to skew the allocation pattern in favour of the better treatment. Bandyopadhyay and Biswas (Biometrika 88 (2001) 409) studied such allocation designs for two competing treatments, when the patients heterogeneous with respect to some prognostic factors and the response from each patient was continuous. In the present paper, we extend the work to the case of missing responses. Under missing at random assumption, we impute for the missing data at every stage depending on the data available at that point in time. We obtain the conditional and unconditional allocation probabilities and the standard error of the estimated treatment difference at each stage. Through simulation, we show that imputation for missing responses under this adaptive design set-up has a clear gain over the method that uses only complete data. The gain is in the sense that the power is larger and the standard error of the estimated treatment difference is smaller.
Download InfoIf you experience problems downloading a file, check if you have the proper application to view it first. In case of further problems read the IDEAS help page. Note that these files are not on the IDEAS site. Please be patient as the files may be large.
Bibliographic InfoArticle provided by Elsevier in its journal Statistics & Probability Letters.
Volume (Year): 70 (2004)
Issue (Month): 1 (October)
Contact details of provider:
Web page: http://www.elsevier.com/wps/find/journaldescription.cws_home/622892/description#description
Please report citation or reference errors to , or , if you are the registered author of the cited work, log in to your RePEc Author Service profile, click on "citations" and make appropriate adjustments.:
- Qihua Wang, 2002. "Empirical Likelihood-based Inference in Linear Models with Missing Data," Scandinavian Journal of Statistics, Danish Society for Theoretical Statistics & Finnish Statistical Society & Norwegian Statistical Association & Swedish Statistical Association, vol. 29(3), pages 563-576.
For technical questions regarding this item, or to correct its authors, title, abstract, bibliographic or download information, contact: (Zhang, Lei).
If references are entirely missing, you can add them using this form.