Conventionally, standard errors of propensity score matching estimates are obtained using bootstrap methods, but with large samples such as those available to this study, it is not feasible to calculate bootstrap standard errors for all estimates.
Support to the dendrogram was obtained using bootstrap (100 replicates).
Nodal support was obtained using bootstrap analysis (1,000 replicates).
The 95% confidence intervals for the AC1 statistics were obtained using bootstrap resampling with 1,000 resamples.
Support for each node was obtained using bootstrap (500 replicates) [ 16].
The confidence intervals for kappa were obtained using bootstrap methods with 5000 replications.
A Minimum Evolution tree (ME, Figure 3A) based on AFLP markers was calculated using PAUP 4.0 [ 56]; support for each node was obtained using bootstrap (1000 replicates, [ 57]).
Standard errors of the contribution of the various factors to the CI are obtained using bootstrap methods with 1,000 replications taking into account the sampling structure of the data set (45, 46).
AUC-ROC were performed to identify optimal cutoff values of Ptr,stim and TFdi in predicting SBT failure, and these estimates were obtained using bootstrapping with 1000 replications.
Confidence intervals for the population prevalence estimates were obtained using bootstrapping in Stata (version 12).
