Revision system | Nested models | Durbin-Koopman state-space form | Estimation in reviser | Example: Euro Area GDP revisions | Other KK-family specifications
Package: reviser 0.1.1
Marc Burri
reviser: Analyzing Revisions in Real-Time Time Series Vintages
Analyzes revisions in real-time time series vintages. The package converts between wide revision triangles and tidy long vintages, extracts selected releases, computes revision series, visualizes vintage paths, and summarizes revision properties such as bias, dispersion, autocorrelation, and news-noise diagnostics. It also identifies efficient releases and estimates state-space models for revision nowcasting. Methods are based on Howrey (1978) <doi:10.2307/1924972>, Jacobs and Van Norden (2011) <doi:10.1016/j.jeconom.2010.04.010>, and Kishor and Koenig (2012) <doi:10.1198/jbes.2010.08169>.
Authors:
reviser_0.1.1.tar.gz
reviser_0.1.1.zip(r-4.7)reviser_0.1.1.zip(r-4.6)reviser_0.1.1.zip(r-4.5)
reviser_0.1.1.tgz(r-4.6-any)reviser_0.1.1.tgz(r-4.5-any)
reviser_0.1.1.tar.gz(r-4.7-any)reviser_0.1.1.tar.gz(r-4.6-any)
reviser_0.1.1.tgz(r-4.6-emscripten)
manual.pdf |manual.html✨
DESCRIPTION |NEWS
card.svg |card.png
reviser/json (API)
| # Install 'reviser' in R: |
| install.packages('reviser', repos = c('https://packages.ropensci.org', 'https://cloud.r-project.org')) |
Reviews:rOpenSci Software Review #709
Bug tracker:https://github.com/ropensci/reviser/issues
Pkgdown/docs site:https://docs.ropensci.org
Datasets:
- gdp - Vintages Data
forecastingmacroeconomicsnowcastingrevisionstime-series
Last updated from:3b9f065cb0 (on main). Checks:10 OK. Indexed: yes.
| Target | Result | Time | Files | Syslog |
|---|---|---|---|---|
| linux-devel-x86_64 | OK | 234 | ||
| pkgdown docs | OK | 371 | ||
| source / vignettes | OK | 279 | ||
| linux-release-x86_64 | OK | 249 | ||
| macos-release-arm64 | OK | 168 | ||
| macos-oldrel-arm64 | OK | 135 | ||
| windows-devel | OK | 190 | ||
| windows-release | OK | 199 | ||
| windows-oldrel | OK | 241 | ||
| wasm-release | OK | 180 |
Exports:colors_reviserdiagnoseget_days_to_releaseget_first_efficient_releaseget_first_releaseget_fixed_releaseget_latest_releaseget_nth_releaseget_releases_by_dateget_revision_analysisget_revisionsjvn_nowcastkk_nowcastplot_vintagesscale_color_reviserscale_fill_revisertheme_reviservintages_longvintages_wide
Dependencies:abindbackportsbootbroomcalculuscarcarDataclicolorspacecowplotcpp11DerivdoBydplyrfarverforecastFormulafracdiffgenericsggplot2gluegtableisobandKFASlabelinglatticelifecyclelme4lmtestlubridatemagrittrMASSMatrixMatrixModelsmgcvmicrobenchmarkminqamodelrnlmenloptrnnetnumDerivpbkrtestpillarpkgconfigpurrrquantregR6rbibutilsRColorBrewerRcppRcppArmadilloRcppEigenRdpackreformulasrlangS7sandwichscalesSparseMstringistringrsurvivalsystemfittibbletidyrtidyselecttimechangetimeDateurcautf8vctrsviridisLitewithrzoo
Nowcasting revisions using the generalized Kishor-Koenig family
Last update: 2026-03-19
Started: 2026-01-12
Nowcasting revisions using the Jacobs-Van Norden model
Revision decomposition | Durbin-Koopman state-space form | The reviser implementation | Measurement equation | Transition equation | Shock-loading matrix | Nested JVN specifications | Example: Euro Area GDP revisions | Other JVN specifications
Last update: 2026-03-19
Started: 2026-01-12
Identifying an Efficient Release in Data Subject to Revisions
Optimal Properties of Revisions | Initial Estimates as Truth Measured with Noise | The Challenge of Defining a Final Release | Iterative Approach for Identifying ( e ) | Importance of an Efficient Release | Example: Identifying an Efficient Release in GDP Data with reviser | References
Last update: 2026-03-19
Started: 2025-03-04
Revision Patterns and Statistics
Summary Statistics | Revision Size | 1. Mean Revision ("Bias (mean)") | 2. Mean Absolute Revision ("MAR") | 3. Minimum and Maximum Revisions ("Minimum", "Maximum") | 4. Percentiles of Revisions ("10Q", "Median", "90Q") | 5. Standard Deviation of Revisions ("Std. Dev.") | 6. Noise-to-Signal Ratio ("Noise/Signal") | Correlation of Revisions | 1. Correlation Between Revisions and Initial Releases ("Correlation") | 2. 1st order Autocorrelation of Revisions ("Autocorrelation (1st)") | 3. Autocorrelation of Revisions up to 1 year ("Autocorrelation up to 1yr (Ljung-Box p-value)") | Sign Switches | 1. Fraction of sign changes | 2. Fraction of sign changes in the growth rate | Hypothesis Tests | News and Noise Tests for Data Revisions | 1. The Noise Test | 2. The News Test | Test of Seasonality in Revisions | Friedman Test | Theil’s U Statistics | 1. Theil’s U1 Statistic ("Theil's U1") | 2. Theil’s U2 Statistic ("Theil's U2") | References
Last update: 2026-03-19
Started: 2025-03-04
Introduction to reviser
Package conventions | Convert Long to Wide Format | Convert Wide to Long Format | Handling Multiple Series with id | Extracting Releases | Visualizing Vintage Data | Analyzing Data Revisions and Releases
Last update: 2026-03-19
Started: 2025-03-04
Understanding Data Revisions
Introduction: Why do data revisions occur? | Incorporation of newly available or updated data | Base data revisions | Benchmark revisions (methodological changes) | Minor changes in estimation methods | Technical adjustments & error corrections | Economic events & shocks | Technological advances in data collection | Some mathematical notation | Extracting revisions with reviser | The get_revisions() function | Example usage | Example 1: Revisions Using an Interval | Example 2: Revisions Relative to a Fixed Reference Date | Example 3: Revisions to the Nth Release | Example 4: How does the growth rate of GDP change over time? | References
Last update: 2026-03-19
Started: 2025-03-04
The Role and Importance of Revisions in Time Series Data
Introduction | Understanding the Magnitude of Revisions | The Dynamics of Revisions and What They Reveal | The Uses of Studying Revisions in Time Series Data | Conclusion
Last update: 2025-03-14
Started: 2025-03-04
