R Observatory: Metrics for DecisionDrift version 0.2.0

Balamuta, James Joseph

doi:10.5281/zenodo.21843040

DecisionDrift

0.2.0Package record

Detecting, Decomposing, and Stress-Testing Temporal Change in Repeated Decision Systems

0packages depend

2.2Kdownloads / year

69.6%test coverage

13/13flavors OK

Overview

About

Maintained by Subir HaitCRAN page ↗GitHub ↗Issues ↗

Tools for detecting, decomposing, and testing temporal change in repeated binary decision systems. Decomposes each change in the decision rate into inflow (uptake) and outflow (reversal) through the marginal-transition identity, separates net change from gross turnover, and splits aggregate change into within-group and composition components with a symmetric midpoint decomposition. A unit-level cluster bootstrap gives intervals for every component and a global test of process stability with family-wise-adjusted contrasts and simultaneous confidence bands. Also provides prevalence and transition drift summaries, entropy trends, group-differential drift, change-point diagnostics, robustness and sensitivity analyses, an integrated audit, and a simulator for stable, marginal, masked, abrupt, group-masked, and composition-change scenarios. Complements the 'decisionpaths' package. Applications include algorithmic audit, AI governance, education, health, and organisational research.

Changes in 0.2.0

New features

dd_decompose() -- flow decomposition of each change in the decision rate into inflow (uptake) and outflow (reversal) using the marginal-transition identity. Reports turnover, net endpoint change (NEC), cumulative marginal burden (CMB), cumulative transition burden (CTB), and, for unbalanced panels, the gap between paired and cross-sectional change.
dd_group_decompose() -- symmetric midpoint decomposition of aggregate change into within-group and composition components, composition drift D_C, and group-specific uptake and reversal. Supports time-varying group membership.
dd_cluster_bootstrap() -- unit-level cluster bootstrap that keeps each unit's full history. One set of draws can be shared by all inference functions.

Show all changes in 0.2.0Hide the rest of the changes in 0.2.0

dd_global_test() -- global test that uptake, reversal, and/or prevalence are constant across waves, overall or by group. Max-t and Wald statistics with a centred bootstrap null; familywise-adjusted p-values and simultaneous confidence bands. Contrasts compare each step with the previous one (contrast = "consecutive", default) or with the first one (contrast = "baseline", more power against gradual drift).
dd_simulate() -- simulate panels under stable, marginal, masked, abrupt, group-masked, and composition-change scenarios, or custom uptake and reversal sequences.
inst/simulation/mc_study.R -- script for the Monte Carlo study comparing the prevalence trend test with the global stability test.
dd_decompose, dd_group_decompose, and dd_global_test have print() and plot() methods.

Changes to existing functions

dd_audit() no longer returns "no drift detected", "marginal drift", "moderate drift", or "strong drift". Those labels came from fixed, uncalibrated cut-offs. The audit now runs one cluster bootstrap, the flow and group decompositions, and dd_global_test(), and returns a conclusion stating the test result at level alpha. verdict is kept as an alias of conclusion. New arguments: global_test, components, alpha, thresholds (user-supplied practical cut-offs), and seed.
dd_changepoint(): the event-alignment result no longer has a "strong"/"weak" evidence label; it returns alpha and a logical significant. Documentation now notes that the wave-level methods have little power with few waves.

Bug fixes

dd_transition(): reversal_drift held the mean absolute change in uptake P(1|0), not reversal. It now holds the mean absolute change in reversal P(0|1). The uptake value is now returned as uptake_drift. TDI values are unchanged. Code that used reversal_drift from 0.1.0 was reading uptake drift and should switch to uptake_drift to keep the old numbers.
dd_transition() and dd_indices() documentation now gives the TDI and CDB formulas in terms of uptake, reversal, and the decision rate.
plot.dd_transition() now shows uptake and reversal.
Repository URLs updated to github.com/subirhait.

From NEWS.md in the release

Install

R (CRAN)pak (dev)Ubuntu (r2u)Fedora (COPR)openSUSE (OBS)

install.packages("DecisionDrift", repos = "https://cloud.r-project.org/")

Installs the current CRAN release. Prebuilt binaries on Windows and macOS.

if (!requireNamespace("pak", quietly = TRUE))
  install.packages("pak", repos = "https://cloud.r-project.org/")
pak::pak("subirhait/DecisionDrift")

Development version from subirhait/DecisionDrift. Installs pak first if it is not already available.

Release

# enable cranapt (r2u) if it is not already set up, then install
grep -rqs r2u.stat.illinois.edu /etc/apt/sources.list /etc/apt/sources.list.d/ \
  || curl -fsSL https://raw.githubusercontent.com/eddelbuettel/r2u/master/inst/scripts/add_cranapt_noble.sh | sudo bash
sudo apt install -y r-cran-decisiondrift

Fast Ubuntu binaries via r2u (no compilation). The cranapt setup runs once and is skipped when it is already enabled. We list this channel from recorded r2u download activity rather than from a live index of the repository, so treat it as last known rather than guaranteed.

bspm (used by r2u) also needs make: sudo apt install make

# enable the iucar/cran COPR if it is not already present, then install
ls /etc/yum.repos.d/*iucar*cran*.repo >/dev/null 2>&1 \
  || sudo dnf copr enable -y iucar/cran
sudo dnf install -y R-CRAN-DecisionDrift

RPMs from the iucar/cran COPR, rebuilt from CRAN.

For install.packages() integration in R, also: sudo dnf install R-CoprManager

# add the autoCRAN OBS repo (Tumbleweed) if it is missing, then install
zypper -q lr | grep -qi autoCRAN \
  || sudo zypper addrepo https://download.opensuse.org/repositories/devel:/languages:/R:/autoCRAN/openSUSE_Tumbleweed/devel:languages:R:autoCRAN.repo
sudo zypper install -y R-DecisionDrift

RPMs auto-built from CRAN on openSUSE OBS (Tumbleweed). We list this channel from recorded autoCRAN download activity rather than from a live index of the repository, so treat it as last known rather than guaranteed.

Health

CRAN checks

13OK

CRAN check page ↗

Slowest check: 2.8 min · r-oldrel-macos-x86_64

Status changes

OK13 OK2026-08-05
NOTE12 OK, 1 NOTE2026-08-01
OK3 OK2026-04-17

Advisories

none known

How this is measured·How advisories are found

Documentation

In release 0.2.0

READMEYes · 638 wordsVignettesYes · 1 · dynamicNEWSYes · 100% structured · mentions 0.2.0Citation fileNoWebsitenot declared in DESCRIPTION

Help pages: 26
Examples that run: 100%15 run in a plain check
Exported functions with examples: 100%
Documented parameters: 97%
Return-value docs: 100%
Help pages citing references: 0%

Vignettes (1)

DecisionDrift: Auditing Temporal Drift in Repeated Decision Systems HTML

How these are measured

Downloads

2.2K

CRAN downloads in the past year

Rank #12,536 · ~6/day · ~186/mo

Releases R versions

Daily download trend is not available in this view yet.

33130 days

89890 days

2.2K1 year

Compare downloads with other packages →

Also on38 r2u2 autocran

How downloads are counted

Repository

subirhait/decisiondrift ↗Account: subirhait

0Stars

0Forks

0Open issues

0Open PRs

0Releases

Last activity 2026-04-12 · The default branch showed an older version (0.1.0) than CRAN on 2026-10-22

Responsiveness

not measured

Earlier repositories

github.com/causalfragility-lab/decisiondrift · last recorded on 2026-10-16

How these are measured

PracticesBeta

2 development-tooling and community-health practices detected across 2 families in the upstream repository

Checks run against github.com/subirhait/decisiondrift on 2026-10-22.

CRAN release process (1)

cran-comments.md

Lint, format, editor (1)

RStudio project

How this is detected·Detection ruleset v4 (2026-10-20)

Dependencies

Declared dependencies

9 external dependencies (excludes base and recommended)

Installing DecisionDrift adds 10 packages (7 with compiled code, 4.0 MB of source tarballs). Heaviest: vctrs 1.0 MB, rlang 766 KB, cli 629 KB.

Depends (1)

R >= 4.1.0

Imports (5)

cli rlangstatstibbleutils

LinkingTo (0)

none

Suggests (6)

decisionpaths ggplot2 knitr patchwork rmarkdown testthat

Enhances (0)

none

Dependency license breakdown →

Reverse dependencies

0direct

0indirect

Nothing depends on this yet.

How these are counted

Code & Tests

People & History

People (1)

Subir Hait

Author, Maintainer since 0.1.0 (2026)

Releases (2)

Pick two releases to compare their code metrics.

0.2.0Latest
record
2026-10-17 · current release · diff ↗ ·
added 5 exports
dd_cluster_bootstrap, dd_decompose, dd_global_test, dd_group_decompose, dd_simulate
·
listed once in CRAN's queue
Seen in one reading of CRAN's incoming queue, at 2026-10-17 02:21 UTC, so it stayed less than the time between readings.
R
R 4.6.0 released · 2026-04-24
0.1.0
record
2026-04-16
R
R 4.5.0 released · 2025-04-11

Across CRAN, the median accepted release of the past year spent 26 hours in the queue, 90% under 11 days.How queue time is measured

Package metadata

First published: 2026-04-16
Total releases: 2 / 1 yrs
License: MIT + file LICENSE OSI
Minimum R: ≥ 4.1.0
Download size: 148 KB

Cite

Cite this package

Run in R for the authors' preferred citation:

citation("DecisionDrift")

Format

Hait, S. (2026). DecisionDrift: Detecting, Decomposing, and Stress-Testing Temporal Change in Repeated Decision Systems (Version 0.2.0) [Computer software]. https://doi.org/10.32614/CRAN.package.DecisionDrift

This package has no citation file, so citation() returns this entry built from DESCRIPTION.

Cite the R Observatory

For a number measured here: a download total, a coverage figure, an archival date.

Format

APA

Balamuta, J. J. (2026). R Observatory: Metrics for DecisionDrift version 0.2.0 [Data set]. HJJB, LLC. Data release v2026-10-24. https://doi.org/10.5281/zenodo.21843040

From data release v2026-10-24, which the citation names so these numbers can be found later. More on citing and the projects behind them.

Report a problem with this page →