The hardware and bandwidth for this mirror is donated by METANET, the Webhosting and Full Service-Cloud Provider.
If you wish to report a bug, or if you are interested in having us mirror your free-software or open-source project, please feel free to contact us at mirror[@]metanet.ch.
rr0 parameter to
sample_size_nbinom() and blinded_ssr() to
support non-inferiority and super-superiority testing.event_gap to 0 in
nb_sim().cut_date_for_completers() to support
nb_sim_seasonal() output (no tte column).calculate_blinded_info() blinded information
calculation to use subject-level exposure.toInteger.gsNB() to avoid unintended power changes
by correctly recomputing information with max_followup,
preserving delta1, and improving ratio-aware integer
rounding.sample_size_nbinom() computes sample size or power for
fixed designs with two treatment groups. Supports piecewise accrual,
exponential dropout, maximum follow-up, and event gaps. Implements the
Zhu and Lakkis (2014) and Friede and Schmidli (2010) methods.gsNBCalendar() creates group sequential designs for
negative binomial outcomes, optionally attaching calendar-time analysis
schedules (via analysis_times) compatible with gsDesign.
Inherits from both gsDesign and
sample_size_nbinom_result classes.compute_info_at_time() computes statistical information
for the log rate ratio at a given analysis time, accounting for
staggered enrollment.toInteger() rounds sample sizes in a group sequential
design to integers while respecting the randomization ratio.nb_sim() simulates recurrent events for trials with
piecewise constant enrollment, exponential failure rates, and piecewise
exponential dropout. Supports negative binomial overdispersion via gamma
frailty and event gaps.nb_sim_seasonal() simulates recurrent events where
event rates vary by season (Spring, Summer, Fall, Winter).sim_gs_nbinom()
runs repeated simulations with flexible cut rules via
get_cut_date(), check_gs_bound() updates
spending bounds based on observed information, and
summarize_gs_sim() summarizes operating characteristics
across analyses.cut_data_by_date() censors follow-up at a specified
calendar time and aggregates events per subject, adjusting for event
gaps.get_analysis_date() finds the calendar time at which a
target event count is reached.cut_completers() subsets data to subjects randomized by
a specified date.cut_date_for_completers() finds the calendar time at
which a target number of subjects have completed their follow-up.mutze_test() fits a negative binomial (or Poisson)
log-rate model and performs a Wald test for the treatment effect,
following Mütze et al. (2019).blinded_ssr() estimates blinded dispersion and event
rate from interim data and re-calculates sample size to maintain power,
following Friede and Schmidli (2010).calculate_blinded_info() estimates blinded statistical
information for the log rate ratio from aggregated interim data.gsDesign(), gsBoundSummary(),
and common spending functions (sfHSD(),
sfLDOF(), sfLDPocock(), and more) for
convenience.These binaries (installable software) and packages are in development.
They may not be fully stable and should be used with caution. We make no claims about them.