se_boot()
to remove CRAN warning.drop = TRUE
when subsetting rows in se_param()
/se_boot()
).calc_nreps2()
by calc_nreps()
to calculate the number of repetitions in the case of multiple (>2) algorithms.calc_se()
now performs point estimate and standard error calculations for all pairs of interest in the case of multiple algorithms.calc_instances()
now returns the number of required instances to maintain the desired power for the family of experiments, based on Holm’s step-down correction. It also returns the sequence of alpha values and the corresponding power to detect the effect size d
, for each comparison using Holm’s method.CAISER_powercurve
and all associated methods (print, summary, plot) as these were (very) rarely used.nreps
with new summary/plotting functions.print
and summary
methods.calc_se()
that resulted in NaN
if two vectors with the same sample mean and same sample variance were passed as arguments.consolidate.partial.results()
)run_experiment()
can now be run in parallel using multiple cores.run_experiment()
and calc_nreps2()
can now save results to files.run_experiment()
now forces the use of all available instances if power >= 1
.