Table 4

The assessment of the association between the absence of medical statistics experts and the use of inappropriate/desirable algorithms in multivariate analysis with adjustment for potential confounders

FactorUsing only significant variables in univariate analysisFitting several models for the same outcome and selected factors
OR95% CIOR95% CI
LowerUpperLowerUpper
Medical statistics experts included as first author or coauthor (vs no experts)0.280.150.533.511.886.58
Medical statistics experts included as first author or coauthor (vs no experts) when  first   author is clinician or other0.420.190.972.361.035.38
  • All models were adjusted for impact factor and the number of events.