Lisa N Yelland1,2, Thomas R Sullivan2, Menelaos Pavlou3, Shaun R Seaman4. 1. Women's and Children's Health Research Institute, North Adelaide, South Australia, Australia. 2. School of Population Health, The University of Adelaide, Adelaide, South Australia, Australia. 3. Department of Statistical Science, University College London, London, UK. 4. MRC Biostatistics Unit, Cambridge, UK.
Abstract
BACKGROUND: Informative birth size occurs when the average outcome depends on the number of infants per birth. Although analysis methods have been proposed for handling informative birth size, their performance is not well understood. Our aim was to evaluate the performance of these methods and to provide recommendations for their application in randomised trials including infants from single and multiple births. METHODS: Three generalised estimating equation (GEE) approaches were considered for estimating the effect of treatment on a continuous or binary outcome: cluster weighted GEEs, which produce treatment effects with a mother-level interpretation when birth size is informative; standard GEEs with an independence working correlation structure, which produce treatment effects with an infant-level interpretation when birth size is informative; and standard GEEs with an exchangeable working correlation structure, which do not account for informative birth size. The methods were compared through simulation and analysis of an example dataset. RESULTS: Treatment effect estimates were affected by informative birth size in the simulation study when the effect of treatment in singletons differed from that in multiples (i.e. in the presence of a treatment group by multiple birth interaction). The strength of evidence supporting the effectiveness of treatment varied between methods in the example dataset. CONCLUSIONS: Informative birth size is always a possibility in randomised trials including infants from both single and multiple births, and analysis methods should be pre-specified with this in mind. We recommend estimating treatment effects using standard GEEs with an independence working correlation structure to give an infant-level interpretation.
BACKGROUND: Informative birth size occurs when the average outcome depends on the number of infants per birth. Although analysis methods have been proposed for handling informative birth size, their performance is not well understood. Our aim was to evaluate the performance of these methods and to provide recommendations for their application in randomised trials including infants from single and multiple births. METHODS: Three generalised estimating equation (GEE) approaches were considered for estimating the effect of treatment on a continuous or binary outcome: cluster weighted GEEs, which produce treatment effects with a mother-level interpretation when birth size is informative; standard GEEs with an independence working correlation structure, which produce treatment effects with an infant-level interpretation when birth size is informative; and standard GEEs with an exchangeable working correlation structure, which do not account for informative birth size. The methods were compared through simulation and analysis of an example dataset. RESULTS: Treatment effect estimates were affected by informative birth size in the simulation study when the effect of treatment in singletons differed from that in multiples (i.e. in the presence of a treatment group by multiple birth interaction). The strength of evidence supporting the effectiveness of treatment varied between methods in the example dataset. CONCLUSIONS: Informative birth size is always a possibility in randomised trials including infants from both single and multiple births, and analysis methods should be pre-specified with this in mind. We recommend estimating treatment effects using standard GEEs with an independence working correlation structure to give an infant-level interpretation.
Authors: Katherine S Panageas; Deborah Schrag; A Russell Localio; E S Venkatraman; Colin B Begg Journal: Stat Med Date: 2007-04-30 Impact factor: 2.373
Authors: Roberta A Ballard; William E Truog; Avital Cnaan; Richard J Martin; Philip L Ballard; Jeffrey D Merrill; Michele C Walsh; David J Durand; Dennis E Mayock; Eric C Eichenwald; Donald R Null; Mark L Hudak; Asha R Puri; Sergio G Golombek; Sherry E Courtney; Dan L Stewart; Stephen E Welty; Roderic H Phibbs; Anna Maria Hibbs; Xianqun Luan; Sandra R Wadlinger; Jeanette M Asselin; Christine E Coburn Journal: N Engl J Med Date: 2006-07-27 Impact factor: 91.245
Authors: Maria Makrides; Robert A Gibson; Andrew J McPhee; Carmel T Collins; Peter G Davis; Lex W Doyle; Karen Simmer; Paul B Colditz; Scott Morris; Lisa G Smithers; Kristyn Willson; Philip Ryan Journal: JAMA Date: 2009-01-14 Impact factor: 56.272
Authors: Ran S Rotem; Gabriel Chodick; Michael Davidovitch; Andrea Bellavia; Marc G Weisskopf Journal: Am J Epidemiol Date: 2022-02-19 Impact factor: 4.897
Authors: Abhik Das; Jon Tyson; Claudia Pedroza; Barbara Schmidt; Marie Gantz; Dennis Wallace; William E Truog; Rosemary D Higgins Journal: Semin Perinatol Date: 2016-06-22 Impact factor: 3.300
Authors: Michelle N Körnmann; Viola Christmann; Charlotte J W Gradussen; Laura Rodwell; Martin Gotthardt; Johannes B Van Goudoever; Arno F J Van Heijst Journal: Nutrients Date: 2017-12-02 Impact factor: 5.717
Authors: Elizabeth Janiak; Isabel R Fulcher; Alischer A Cottrill; Nicole Tantoco; Ashley H Mason; Jennifer Fortin; Jamie Sabino; Alisa B Goldberg Journal: Obstet Gynecol Date: 2019-05 Impact factor: 7.661