dot-block_bootstrap: Apply block-bootstrapping procedure to module input

In covid-19-Re/estimateR: Reproductive number estimation from delayed observations of infections

Apply block-bootstrapping procedure to module input

Description

.block_bootstrap returns a block-bootstrapped replicate of the incidence. Incidence should be a vector of non-negative values

Usage

.block_bootstrap(
  incidence_input,
  round_incidence = TRUE,
  smoothing_method = "LOESS",
  ...
)

Arguments

incidence_input	Module input object. List with two elements: A numeric vector named values: the incidence recorded on consecutive time steps. An integer named index_offset: the offset, counted in number of time steps, by which the first value in values is shifted compared to a reference time step This parameter allows one to keep track of the date of the first value in values without needing to carry a date column around. A positive offset means values are delayed in the future compared to the reference values. A negative offset means the opposite.
round_incidence	boolean. If TRUE, the bootstrapped incidence is rounded to the nearest integer.
smoothing_method	string. Method used to smooth the original incidence data. Available options are: 'LOESS', implemented in .smooth_LOESS
...	Arguments passed on to .block_bootstrap_overlap_func, smooth_incidence block_size integer. Size of a bootstrapping block. keep_weekdays_aligned boolean. Set to FALSE if not daily incidence, or if no weekly noise pattern that would require to apply errors to the same day of the week as they were in the original data.

Details

This function works by resampling blocks of differences (on the log-scale) between the original data and a smoothed version of the original data.

Value

a module output object. bootstrapped incidence.

covid-19-Re/estimateR documentation built on Sept. 14, 2024, 5:49 a.m.