Build a discretized probability distribution vector — build_delay

The discretization is done by integrating the probability density on (0, 0.5), (0.5, 1.5), (1.5, 2.5)...

build_delay_distribution(
  distribution,
  max_quantile = 0.999,
  offset_by_one = FALSE
)

Arguments

distribution	list. probability distribution specified in list format e.g. list(name = "gamma", shape = 2, scale = 4). The `distribution` list must contain a 'name' element, this element must be a string and correspond to one of the types of `distributions` supported in the Distributions package. `distribution` must also contain parameters for the specified distribution, in the form '`parameter_name=parameter_value`'.
max_quantile	numeric value between 0 and 1. Upper quantile reached by the last element in the discretized distribution vector.
offset_by_one	boolean. Set to TRUE if `distribution` represents the fit of data that was offset by one (`fitted_data = original_data + 1`) to accommodate zeroes in `original_data`.

Value

vector containing the discretized probability distribution vector of distribution.

Examples

## Obtaining the discretized probabiility vector for different distributions

gamma_distribution <- list(name= "gamma", shape = 3.2, scale = 1.3)
delay_distribution_vector_1 <- build_delay_distribution(gamma_distribution)

normal_distribution <- list(name = "norm", mean = 5, sd = 2)
delay_distribution_vector_2 <- build_delay_distribution(normal_distribution)

uniform_distribution <- list(name = "unif", min = 0.5, max = 4)
delay_distribution_vector_3 <- build_delay_distribution(uniform_distribution)