That takes the BISCUIT: A comparative study of predictive accuracy and parsimony of four statistical learning techniques in personality data, with data missingness conditions

The predictive accuracy of personality-criterion regression models may be improved with statistical learning (SL) techniques. This study introduced a novel SL technique, BISCUIT (Best Items Scale that is Cross-validated, Unit-weighted, Informative and Transparent). The predictive accuracy and parsimony of BISCUIT was compared with three established SL techniques (the lasso, elastic net, and random forest) and regression using two sets of scales, for five criteria, across five levels of data missingness. BISCUIT’s predictive accuracy was competitive with other SL techniques at higher levels of data missingness. BISCUIT most frequently produced the most parsimonious SL model. The elastic net and lasso dominated other techniques in terms of predictive accuracy with complete data and in conditions with up to 50% data missingness. In terms of predictive accuracy, regression using 27 narrow traits was an intermediate choice. For most criteria and levels of data missingness, regression using the Big Five had the worst predictive accuracy. Overall, loss in predictive accuracy due to data missingness was modest, even at 90% data missingness. Findings suggest that personality researchers should consider incorporating planned data missingness and SL techniques into their designs and analyses.