R Observatory: Metrics for effectcheck version 0.7.17

Balamuta, James Joseph

doi:10.5281/zenodo.21843040

effectcheck

0.7.17Package record

Statistical Consistency Checker for Published Research Results

0packages depend

3Kdownloads / year

86.6%test coverage

13/13flavors OK

Overview

About

Maintained by Gilad FeldmanCRAN page ↗GitHub ↗Issues ↗

A conservative, assumption-aware statistical consistency checker for already-extracted research-results text. Parses test statistics, effect sizes, and confidence intervals across multiple citation styles including American Psychological Association (APA), Harvard, Frontiers, PLOS ONE, Scientific Reports, Nature Human Behaviour, PeerJ, eLife, PNAS, and others. Recomputes effect sizes using all plausible variants when design is ambiguous, and validates internal consistency. Supports t-tests, F-tests/ANOVA, correlations, chi-square, z-tests, regression, and nonparametric tests. Explicitly tracks all assumptions and uncertainty in output. Detects decision errors (significance reversals) similar to 'statcheck'. From v0.4.0 file extraction is no longer part of the package — pair with an external extractor (e.g., 'docpluck' at https://docpluck.app) and pass the resulting text to check_text(). Note: this package is under active development and results should be independently verified. Use is at the sole responsibility of the user. Contributions and verification reports are welcome.

Changes in 0.7.17

Welch t-test effect sizes (changes verdicts on Welch rows with a stated N far above df + 2 only)

**A stated sample size that already reproduces the reported d is no longer replaced.** A Welch df only bounds N from below (N >= df + 2), so a stated N far above df + 2 is legitimate when variances and group sizes are unequal. The Welch branch treated any scraped N above 1.5 x (df + 2) as "likely from a different study" and replaced it with a value chosen from the reported d itself. Measured at 0.7.16 on "N = 300 participants ... Welch t(150.2) = 0.24, p = .81, d = X": the correct d = 0.03 (2 x 0.24 / sqrt(300) = 0.028) read NOTE with N back-solved to 256, while d = 0.04 read PASS at a swapped N = 152, so the correct value graded worse than a wrong one and the N a row was checked against depended on the value being checked. The override now fires only when the equal-n d at the stated N misses the reported d by more than the effect-size tolerance and its rounding (the cases it was built for, a global N of 794 or 827 contradicting the reported d, still take it). A kept N is named in assumptions_used. Test: tests/testthat/test-v0717-welch-stated-n-kept.R (watched failing first).

Show all changes in 0.7.17Hide the rest of the changes in 0.7.17

**The d tolerance was audited for tiny effects and left unchanged.** d = 0.04 against an equal-n 0.028 still grades PASS, through the same absolute tolerance (0.02) any row with N in its own clause gets. Welch versus pooled-SD conventions and two-decimal rounding spread legitimate printed values over roughly 0.017-0.039 at this t, so a tolerance tight enough to flag 0.04 would flag correct values. At very small d a PASS means "not contradicted", not "verified to two decimals". Cross-checked by a second model (Sonnet, tier 2), which agreed on both points and found three gaps fixed here (no note for a kept N, the g path used the d tolerance, a missing t could error).

From NEWS.md in the release

Install

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

install.packages("effectcheck", 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("giladfeldman/escicheck")

Development version from giladfeldman/escicheck. 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-effectcheck

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-effectcheck

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-effectcheck

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: 9.0 min · r-oldrel-macos-x86_64

Status changes

OK13 OK2026-08-05
NOTE12 OK, 1 NOTE2026-08-01
OK12 OK2026-04-25
NOTE10 OK, 1 NOTE2026-03-28
OK7 OK2026-03-26

Advisories

none known

How this is measured·How advisories are found

Documentation

In release 0.7.17

READMEYes · 2,212 wordsVignettesYes · 1 · dynamicNEWSYes · 67% structured · mentions 0.7.17Citation fileNoWebsitenot declared in DESCRIPTION

Help pages: 114 (81 internal)includes a package overview page
Examples that run: 77%24 run in a plain check · 7 only when donttest examples are enabled (R CMD check --as-cran)
Exported functions with examples: 71%
Documented parameters: 97%
Return-value docs: 100%
Help pages citing references: 0%

Vignettes (1)

Introduction to effectcheck HTML

How these are measured

Downloads

3K

CRAN downloads in the past year

Rank #7,841 · ~8/day · ~253/mo

Releases R versions

Daily download trend is not available in this view yet.

48930 days

1.2K90 days

3K1 year

Compare downloads with other packages →

Also on344 r2u1 autocran

How downloads are counted

Repository

giladfeldman/escicheck ↗Account: giladfeldman

0Stars

0Forks

1Open issues

0Open PRs

0Releases

Last activity 2026-10-08

Responsiveness

How these are sampled

PRs merged (all time): 91%
Median days to close, 50 most recently updated closed issues: not measured
Median days to close, 50 most recently updated closed PRs: not measured

Issues over time

2026-07-07 · 02026-08-27 · 1

How these are measured

PracticesBeta

6 development-tooling and community-health practices detected across 4 families in the upstream repository

Checks run against github.com/giladfeldman/escicheck on 2026-10-18.

Continuous integration (2)

GitHub ActionsR CMD check workflow

The R CMD check workflow runs on Linux

Governance and community (2)

Contributing guideCODEOWNERS

CRAN release process (1)

cran-comments.md

Research and citation (1)

CITATION.cff

How this is detected·Detection ruleset v3 (2026-09-26)

AI coding toolsBeta

This repository shows signs of AI coding tools.

Claude Codefirst seen on or before 2026-03-14
Named in .Rbuildignore: .claude
Commits: at least 56 crediting it in the message

Models named in its commits

Claude Opus 4.656 commits · Mar to Apr 2026

Counts are commits, not lines of code. Commits by a tool's accounts count once across all of its accounts. Commits crediting it are the largest count among its credit lines, a minimum.How this is detected·Detection ruleset v4 (updated 2026-09-27)

Dependencies

Declared dependencies

19 external dependencies (excludes base and recommended)

Installing effectcheck adds 19 packages (11 with compiled code, 18 MB of source tarballs). Heaviest: stringi 11 MB, logger 1.1 MB, vctrs 1.0 MB.

Depends (1)

R >= 4.1.0

Imports (10)

stringr stringi dplyr purrr tibble glue loggergraphicsstatsutils

LinkingTo (0)

none

Suggests (12)

shiny shinythemes DT knitr rmarkdown testthat (>= 3.0.0)MBESS effectsize jsonlite statcheck xml2 rvest

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)

Gilad Feldman

Author, Maintainer since 0.2.3 (2026)

Releases (2)

Pick two releases to compare their code metrics.

0.7.17Latest
record
2026-10-08 · current release · diff ↗ ·
removed 1 export
extract_pdf_comprehensive
·
listed once in CRAN's queue
Seen in one reading of CRAN's incoming queue, at 2026-10-08 14:16 UTC, so it stayed less than the time between readings.
R
R 4.6.0 released · 2026-04-24
0.2.3
record
2026-03-25
R
R 4.5.0 released · 2025-04-11

Across CRAN, the median accepted release of the past year spent 23 hours in the queue, 90% under 11 days.How queue time is measured

Package metadata

First published: 2026-03-25
Total releases: 2 / 1 yrs
License: MIT + file LICENSE OSI
Minimum R: ≥ 4.1.0
Download size: 712 KB

Cite

Cite this package

Run in R for the authors' preferred citation:

citation("effectcheck")

Format

Feldman, G. (2026). effectcheck: Statistical Consistency Checker for Published Research Results (Version 0.7.17) [Computer software]. https://doi.org/10.32614/CRAN.package.effectcheck

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

The repository also keeps a CITATION.cff.

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 effectcheck version 0.7.17 [Data set]. HJJB, LLC. Data release v2026-10-22. https://doi.org/10.5281/zenodo.21843040

From data release v2026-10-22, 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 →