Sentence examples for bootstrap samples were calculated from inspiring English sources
The consensus bipartitions for 100 bootstrap samples were calculated using the CONSENSE program of the PHYLIP package (Felsenstein 1993).
To investigate the assumption of negligible standard error of expected survival and negligible correlation between absolute and expected survival, standard errors for non-standardised expected survival were estimated by bootstrapping, and Pearson's correlation coefficients of the point estimates of non-standardised absolute and expected survival in the bootstrap samples were calculated.
To obtain the distribution denoting the difference in PSI, or ΔPSI, the difference between bootstrap samples was calculated for all pairs of tissues to generate a distribution in the same manner.
The mean costs in each bootstrap sample were calculated for both groups, together with the difference between the two mean costs.
One hundred bootstrap samples were generated for each gene family using the SEQBOOT program of the PHYLIP package (Felsenstein 1993), and distance matrices were calculated for each bootstrap sample in Tree-Puzzle version 5.2 using shape parameters estimated for the original alignment (see above).
The covariance structure software AMOS [ 30] was used to calculate the estimate path coefficients using a bootstrapping method (2000 bootstrap samples were used) [ 31].
One thousand bootstrap samples were taken from the original sample with replacement, and a value of T calculated in each bootstrap sample, denoted for the ith bootstrap sample.
Bootstrapping with 1,000 bootstrap samples was also used to calculate the CI of differences between Brier scores.
Empirical power (calculated using 1000 bootstrap samples) was 85% for this comparison, and on average 33% (range 13 43) for the non-significant comparisons.
Bootstrap estimates (2000 samples drawn) were calculated to derive unbiased confidence intervals [ 33] for the final model.
