Movatterモバイル変換

cld:Compact Letter Display for Statistical Comparisons

Updated-on

Simplify your statistical reporting with compact letterdisplays

Thecld package provides an easy and consistent wayto create compact letter displays (CLDs) for visualizing results ofpairwise statistical comparisons. Groups sharing the same letter are notsignificantly different from each other — a convention widely used inagricultural, biological, and statistical publications.

Why Use cld?

Key Features:

🔄Universal compatibility - Works with base R,PMCMRplus, rstatix, DescTools, and custom formats
🎯One function -make_cld() handlesall input types automatically
📊Publication-ready - Clean, professionalstatistical grouping labels
📝Informative - Stores metadata (alpha, method,comparison counts)
🛠️Well-tested - Comprehensive unit tests ensurereliability

Installation

Install the stable version from CRAN:

install.packages("cld")

Install the development version fromGitHub:

# install.packages("devtools")devtools::install_github("GegznaV/cld")

Quick Start

Thecld package works with various statistical testoutputs. Here’s a simple example:

library(cld)# Run a pairwise testtest_result<-pairwise.wilcox.test(chickwts$weight, chickwts$feed,exact =FALSE)# Generate compact letter displaymake_cld(test_result)#>      group cld spaced_cld#>     casein   a        a__#>  horsebean   b        _b_#>    linseed  bc        _bc#>   meatmeal  ac        a_c#>    soybean   c        __c#>  sunflower   a        a__

Interpretation:

Groups sharing at least one letter arenotsignificantly different (e.g., casein and sunflower both have “a”);
Groups with no shared lettersare significantlydifferent (e.g., horsebean “b” and soybean “c”).

Supported Input Formats

Themake_cld() function works seamlessly with:

Input Type	Example Packages	Function Examples
`pairwise.htest`	base R	`pairwise.t.test()`,`pairwise.wilcox.test()`
`PMCMR` /`PMCMRplus`	PMCMR, PMCMRplus	`kwAllPairsConoverTest()`,`dunnTest()`
`data.frame` (rstatix)	rstatix	`games_howell_test()`,`tukey_hsd()`
`PostHocTest`	DescTools	`ConoverTest()`,`DunnettTest()`
`matrix`	Custom	Symmetric p-value matrices
`data.frame`	Custom	Custom comparison data frames
`formula`	Custom	Formula interface for data frames

Learn More

📚Comprehensive vignettes (also available onpackage website):

vignette("cld") - Complete introduction withexamples
vignette("cld-input-formats") - Detailed examples forall input types
vignette("cld-interpretation-guide") - How to correctlyinterpret CLDs
vignette("cld-advanced-features") - Advanced featuresand custom parameters

Related Packages

Package	Purpose	Relationship to cld
multcompView	CLD algorithm	Used internally bycld
rcompanion	Statistical functions	Alternative CLD implementation
PMCMRplus	Post-hoc tests	Compatible input forcld
rstatix	Tidy statistics	Compatible input forcld
DescTools	Statistical tools	Compatible input forcld

Getting Help

📖 Function reference:?cld::make_cld
📚 Package website:https://gegznav.github.io/cld/
🐛 Report bugs:https://github.com/GegznaV/cld/issues
💬 Ask questions:GitHubDiscussions

Citation

To cite thecld package in publications:

citation("cld")

License

GPL-3

[8]ページ先頭