Package: rtForecastEval 0.0.0.9000

rtForecastEval: Evaluate the Discrepancy between Two Real-Time Updated Probabilistic Forecasts

Methods from Yeh, Rice, and Dubin (2022, doi:10.1080/00031305.2021.1967781; arXiv:2010.00781) for comparing two continuously updated probabilistic forecasts under squared (Brier) loss: pointwise loss and variance, a global delta test (Monte Carlo p-values), simulation designs, and a naive pointwise band plot.

Authors:Chi-Kuang Yeh [aut, cre], Gregory Rice [ctb, ths], Joel A. Dubin [ctb, ths]

rtForecastEval_0.0.0.9000.tar.gz
rtForecastEval_0.0.0.9000.zip(r-4.7)rtForecastEval_0.0.0.9000.zip(r-4.6)rtForecastEval_0.0.0.9000.zip(r-4.5)
rtForecastEval_0.0.0.9000.tgz(r-4.6-any)rtForecastEval_0.0.0.9000.tgz(r-4.5-any)
rtForecastEval_0.0.0.9000.tar.gz(r-4.7-any)rtForecastEval_0.0.0.9000.tar.gz(r-4.6-any)
rtForecastEval_0.0.0.9000.tgz(r-4.6-emscripten)
manual.pdf |manual.html✨
card.svg |card.png
rtForecastEval/json (API)

# Install 'rtForecastEval' in R:

install.packages('rtForecastEval', repos = c('https://chikuang.r-universe.dev', 'https://cloud.r-project.org'))

Bug tracker:https://github.com/chikuang/rtforecasteval/issues

On CRAN:

forecasting goodness-of-fit

4.00 score 1 stars 448 downloads 7 exports 40 dependencies

Last updated from:e62298f2bc. Checks:9 OK. Indexed: yes.

Target	Result	Time
linux-devel-x86_64	OK	152
source / vignettes	OK	231
linux-release-x86_64	OK	148
macos-release-arm64	OK	142
macos-oldrel-arm64	OK	164
windows-devel	OK	102
windows-release	OK	90
windows-oldrel	OK	98
wasm-release	OK	141

Exports:calc_eig calc_L_s2 calc_pval calc_Z df_gen lin_interp plot_pcb

Dependencies:cli cpp11 data.table dplyr farver generics ggplot2 glue gtable isoband jsonlite labeling lattice lifecycle magrittr MASS Matrix pillar pkgconfig purrr R6 RColorBrewer Rcpp RcppEigen rlang rlist RSpectra S7 scales stringi stringr tibble tidyr tidyselect utf8 vctrs viridisLite withr XML yaml

rtForecastEval guide

| Chi-Kuang Yeh (Georgia State University); Gregory Rice, Joel A. Dubin (University of Waterloo)

Rendered fromrtForecastEval-vignette.Rmdusingknitr::rmarkdownon May 29 2026.

Last update: 2026-04-14
Started: 2026-04-09

Citation

Development and contributors

Readme and manuals

Help Manual

Help page	Topics
rtForecastEval: Compare real-time probabilistic forecasts	rtForecastEval-package (Brier-type) (e.g. (NBA ([`calc_L_s2()`]), delta additional and associated bands. blocks building calibration Carlo companion comparing confidence continuously Core covariance data designs difference draws Dubin eigenvalues estimate exports for forecasts form from Implements in in-game is its leading loss loss. mean Monte naive obtain of p-values package package; paper; plots) pointwise probabilistic probabilities) quantiles related replication repository reproduces Rice, rtForecastEval separate simulation squared statistic statistical steps: surfaces, test test The the there. this tools two under updated used variance win workflow, Yeh, [`calc_eig()`], [`calc_pval()`]. [`calc_Z()`], [`df_gen()`] [`plot_pcb()`]
Leading eigenvalues for the delta test covariance	calc_eig
Pointwise mean loss difference and variance	calc_L_s2
Monte Carlo p-value and quantiles for the delta test	calc_pval
Delta test statistic for comparing two forecasting methods	calc_Z
Simulate real-time probabilistic forecasts (paper designs)	df_gen
Linear interpolation of a forecast trajectory onto a grid	lin_interp
Naive pointwise confidence band for mean loss difference	plot_pcb