“…They would be validated by cross-validation; it means we need at least 2 different sets of cohort data-the prediction model derived from one sample would be validated in a second sample. 2,3 Therefore, longitudinal studies are essential for making assumptions for clinical prediction models, but in the study of Sophocleous et al, 1 determination of independent predictors of bone mineral density was done in a cross-sectional study. In other words, the temporality assumption (the dependent variable has to occur after the independent variable) must be ensured in the prediction model.…”