Handling missing data in RCTs; a review of the top medical journals.

Bell ML, Fiero M, Horton NJ, Hsu CH. · 2014

Read Handling missing data in RCTs; a review of the top medical journals. by Bell ML, Fiero M, Horton NJ, Hsu CH. (2014) in the Tower of Babel, a free online library of public-domain works preserved in clean, searchable text. No sign-up. The full text is served as a plain-text file at a predictable URL, where text is present: https://antarctic-labs.com/tower-of-babel/europmc-pmc4247714.txt.

Description

Melanie L. Bell, Nicholas J. Horton, and two co-authors audited how top journals handle missing trial data in BMC Medical Research Methodology in 2014. Randomized trials lose outcome data when patients drop out or miss visits, and gaps can bend the result. The handling a trial chooses, and whether it says so, decides how much readers should trust the numbers.

Reviewing randomized trials from 2013 in four leading journals, they found 73 of 77 papers had some missing outcome data, a median of 9 percent of participants. Dropping incomplete cases was still the commonest fix, at 45 percent, ahead of imputation and model-based methods; only 8 percent used multiple imputation. Just over a third ran a sensitivity check, and intention-to-treat meant different things in different papers. Little had changed since a 2001 review.

Catalog record

CREATORBell ML, Fiero M, Horton NJ, Hsu CH.
YEAR2014
COLLECTIONPAPERS
FORMATTXT
FILE SIZE33 KB
LICENSECC BY 4.0
RIGHTSCC BY
SOURCEEurope PMC

Source: https://europepmc.org/articles/PMC4247714

Browse the full library · About the Tower of Babel