simulate {singleRcapture}

Generating data in singleRcapture

Description

An S3 method for stats::simulate to handle singleRStaticCountData and singleRfamily classes.

Usage

## S3 method for class 'singleRStaticCountData'
simulate(object, nsim = 1, seed = NULL, ...)

## S3 method for class 'singleRfamily'
simulate(object, nsim, seed = NULL, eta, truncated = FALSE, ...)

Arguments

object

an object representing a fitted model.

nsim

a numeric scalar specifying:

• number of response vectors to simulate in simulate.singleRStaticCountData, defaults to 1L.

• number of units to draw in simulate.singleRfamily, defaults to NROW(eta).

seed

an object specifying if and how the random number generator should be initialized (‘seeded’).

...

additional optional arguments.

eta

a matrix of linear predictors

truncated

logical value indicating whether to sample from truncated or full distribution.

Value

a data.frame with n rows and nsim columns.

Author(s)

Maciej Beręsewicz, Piotr Chlebicki

See Also

stats::simulate() estimatePopsize()

Examples

N <- 10000
###gender <- rbinom(N, 1, 0.2)
gender <- rep(0:1, c(8042, 1958))
eta <- -1 + 0.5*gender
counts <- simulate(ztpoisson(), eta = cbind(eta), seed = 1)
df <- data.frame(gender, eta, counts)
df2 <- subset(df, counts > 0)
### check coverage with summary
mod1 <-  estimatePopsize(
  formula       = counts ~ 1 + gender, 
  data          = df2, 
  model         = ztpoisson, 
  controlMethod = list(silent = TRUE)
)
mod1_sims <- simulate(mod1, nsim=10, seed = 1)
colMeans(mod1_sims)
mean(df2$counts)