Statistical analysis plan .pdf
Original filename: Statistical analysis_plan.pdf
Author: Hanne Trap Wolf
This PDF 1.5 document has been generated by Microsoft® Word 2010, and has been sent on pdf-archive.com on 31/01/2018 at 11:06, from IP address 128.0.x.x.
The current document download page has been viewed 150 times.
File size: 151 KB (1 page).
Privacy: public file
Download original PDF file
Data analysis plan:
The primary data analysis will be performed for all enrolled patients on an intention-to-treat basis.
Per protocol data and sensitivity analyses on primary outcomes will be shown in supplementary
material. Confounder control of baseline characteristics will not be performed due to the
randomized study design.
Dichotomous outcomes will be compared between the groups using a logistic regression model and
continuous outcomes by use of a linear model both with adjustment for gestational age, plurality
and center of enrollment. The outcomes from the logistic regressions will be presented as odds
ratios with 95% confidence intervals and outcomes from the linear models as mean differences with
95% confidence intervals. Robust variance estimation will be used to account for clustering of
infants within mothers.
The significance threshold will be set at P of less than 0.05. No interim analyses will be performed
during the study period. Analyses will be performed with the use of SAS software, version 9.4.
It is likely that the study will not have the power individually to detect a significant difference
between magnesium sulphate and placebo. Instead, the results will be added to an existing metaanalysis followed by a trial-sequential analysis as described by Huusom et al (1).
Huusom LD, Secher NJ, Pryds O, Whitfield K, Gluud C, Brok J. Antenatal magnesium
sulphate may prevent cerebral palsy in preterm infants-but are we convinced? Evaluation of
an apparently conclusive meta-analysis with trial sequential analysis. BJOG. 2011;118(1):1–