gsDesignNB (version 0.2.6)

nb_sim_seasonal: Simulate recurrent events with seasonal rates

Description

Simulates recurrent events where event rates depend on the season.

Usage

nb_sim_seasonal(
  enroll_rate,
  fail_rate,
  dropout_rate = NULL,
  max_followup = NULL,
  randomization_start_date = NULL,
  n = NULL,
  block = c(rep("Control", 2), rep("Experimental", 2))
)

Value

A data frame of class nb_sim_seasonal with columns: id, treatment, season, enroll_time, start, end, event, calendar_start, calendar_end. Rows represent intervals of risk or events. event=1 indicates an event at end. event=0 indicates censoring or end of a seasonal interval at end.

Arguments

enroll_rate

A data frame with columns rate and duration.

fail_rate

A data frame with columns treatment, season, rate, and optionally dispersion. Seasons should be "Spring", "Summer", "Fall", "Winter".

dropout_rate

A data frame with columns treatment, rate, duration.

max_followup

Numeric. Max follow-up duration (years).

randomization_start_date

Date. Start of randomization.

n

Integer. Total sample size.

block

Character vector for block randomization.

Examples

enroll_rate <- data.frame(rate = 20 / (5 / 12), duration = 5 / 12)
fail_rate <- data.frame(
  treatment = rep(c("Control", "Experimental"), each = 4),
  season = rep(c("Winter", "Spring", "Summer", "Fall"), times = 2),
  rate = c(0.6, 0.5, 0.4, 0.5, 0.4, 0.3, 0.2, 0.3)
)
sim <- nb_sim_seasonal(
  enroll_rate = enroll_rate,
  fail_rate = fail_rate,
  max_followup = 1,
  randomization_start_date = as.Date("2020-01-01"),
  n = 20
)
head(sim)