Dear Allstat Apologies if this has been mentioned previously. Is there a consensus of view that it is preferable to use the term 'multivariable' to describe models with a single outcome and multiple predictors, rather than the term 'multivariate'? Or does 'multivariable' introduce more confusion than it's worth? See http://www.ncbi.nlm.nih.gov/pmc/articles/PMC3518362/ for example, for background. Trevor Lambert NDPH, Oxford University You may leave the list at any time by sending the command SIGNOFF allstat to [log in to unmask], leaving the subject line blank.