AI Article Synopsis
- Frequentist performance is important for methods used in confirmatory clinical trials, but it alone doesn't validate the use of certain missing data imputation methods.
- Reference-based conditional mean imputation can lead to misleading results, as its variance estimation gets smaller with more missing data.
- This approach can inadvertently suggest that the true treatment effect is zero for patients with missing data, which is not a desirable outcome.
Article Abstract
Accurate frequentist performance of a method is desirable in confirmatory clinical trials, but is not sufficient on its own to justify the use of a missing data method. Reference-based conditional mean imputation, with variance estimation justified solely by its frequentist performance, has the surprising and undesirable property that the estimated variance becomes smaller the greater the number of missing observations; as explained under jump-to-reference it effectively forces the true treatment effect to be exactly zero for patients with missing data.
Download full-text PDF |
Source |
|---|---|
| http://dx.doi.org/10.1002/pst.2373 | DOI Listing |
Publication Analysis
Top Keywords
reference-based conditional
8
frequentist performance
8
missing data
8
comments 'standard
4
'standard reference-based
4
conditional imputation'
4
imputation' regulators
4
regulators trial
4
trial statisticians
4
statisticians aware!
4
Similar Publications
Want AI Summaries of new PubMed Abstracts delivered to your In-box?
Enter search terms and have AI summaries delivered each week - change queries or unsubscribe any time!