Skip to main content
Fig. 6 | BMC Medical Research Methodology

Fig. 6

From: Assessment of predictive performance in incomplete data by combining internal validation and multiple imputation

Fig. 6

Choice of number of resamples B and imputations M in practice. Standard deviation of performance estimate (AUC for performance, ΔAUC for added performance) across 10 runs, averaged across 10 simulated data sets for strategies Val-MI and MI(-y)-Val based on bootstrapping at varying B and M. Apart from the parameters provided in the legend, parameters were chosen as in Fig. 3. In the case of added performance, the number of variables in the baseline model was set to p0=1

Back to article page

BMC Medical Research Methodology

ISSN: 1471-2288

Contact us