PubMed ID:
19675667
Public Release Type:
Journal
Publication Year: 2009
Affiliation: Department of Biostatistics, School of Public Health, University of Alabama at Birmingham, Birmingham, Alabama, United States of America.
DOI:
https://doi.org/10.1371/journal.pone.0006624
Authors:
Allison DB,
Brock DW,
Coffey CS,
Desmond RA,
Elobeid MA,
Gadde KM,
Heymsfield SB,
Lu K,
McVie T,
Musser B,
Padilla MA,
St-Onge MP,
Thomas O
Request IDs:
87
Studies:
Diabetes Prevention Program
Dropouts and missing data are nearly-ubiquitous in obesity randomized controlled trails, threatening validity and generalizability of conclusions. Herein, we meta-analytically evaluate the extent of missing data, the frequency with which various analytic methods are employed to accommodate dropouts, and the performance of multiple statistical methods.