scoringutils (version 0.1.7.2)

pit_df_fast: Probability Integral Transformation (data.frame Format, fast version)

Description

Wrapper around `pit()` for fast use in data.frames. This version of the pit does not do allow any plotting, but can iterate over categories in a data.frame as specified in the `by` argument.

Usage

pit_df_fast(data, n_replicates = 100, by = by)

Arguments

data

a data.frame with the following columns: `true_value`, `prediction`, `sample`

n_replicates

the number of tests to perform, each time re-randomising the PIT

by

character vector with categories to iterate over

Value

the input data.frame (not including rows where prediction is `NA`), with added columns `pit_p_val` and `pit_sd`

Details

see pit

References

Sebastian Funk, Anton Camacho, Adam J. Kucharski, Rachel Lowe, Rosalind M. Eggo, W. John Edmunds (2019) Assessing the performance of real-time epidemic forecasts: A case study of Ebola in the Western Area region of Sierra Leone, 2014-15, <doi:10.1371/journal.pcbi.1006785>

Examples

# NOT RUN {
example <- scoringutils::continuous_example_data
result <- pit_df(example, full_output = TRUE)

# }