The hardware and bandwidth for this mirror is donated by dogado GmbH, the Webhosting and Full Service-Cloud Provider. Check out our Wordpress Tutorial.
If you wish to report a bug, or if you are interested in having us mirror your free-software or open-source project, please feel free to contact us at mirror[@]dogado.de.
testthat test suite covering
TukeyC with formula, aov, and
lm inputs for balanced and unbalanced designs, as well as
summary, print, plot, and
xtable methods.TukeyC_intro (HTML, via R
Markdown) and TukeyC_intro_pdf (PDF, via knitr/LaTeX),
covering quick start, accepted input classes, unbalanced data, RCBD,
factorial and split-plot designs, visualisation options, tabular output,
and mixed models.make.TukeyC.groups(): refactored letter-grouping with
sequential scanning and homogeneity checks for non-transitive pairwise
patterns under unbalanced designs; added
tests/testthat/test-make-TukeyC-groups.R.make.TukeyC.test(): Result table now uses
a named Means column combined with letter columns from
make.TukeyC.groups().m.infos.lmerMod() and
m.infos.nest.lmerMod(): detect emmeans CI
column names dynamically (lower.CL/upper.CL or
asymp.LCL/asymp.UCL).summary.TukeyC(): corrected message typo (“Groups” vs
“Goups”).plot.TukeyC documentation: di= /
disp= replaced with dispersion=.README.md fully rewritten: badges (CRAN status,
downloads, checks, lifecycle, licence), key features, installation
instructions (CRAN and GitHub), quick-start examples, project layout,
contributing guide, and roadmap.DESCRIPTION: version bumped to 1.4-0; author fields
standardised to match the ScottKnott package template;
R (>= 4.0.0); added BugReports URL and LEC
software page; added knitr, rmarkdown, and
testthat (>= 3.0.0) to Suggests; set
VignetteBuilder: knitr and
Config/testthat/edition: 3.NEWS.md (this file), migrated from the historical
ChangeLog.plot.TukeyC(): removed the none dispersion
option; default is now mm (min–max range), matching
plot.SK().xtable.TukeyC(): treatment names moved from row names
to an explicit Treatment column; added
print.xtable.TukeyC() S3 method that strips the
inconsistent 2-space indentation inserted by print.xtable
in compiled LaTeX and HTML tables.R/ source files reformatted for consistent 2-space
indentation, spacing around operators, and readable line breaks; mixed
tabs and trailing whitespace eliminated throughout.man/: author fields standardised to scientific name
order (Faria, J. C.; Jelihovschi, E. G.; Allaman, I. B.), matching the
ScottKnott package.ChangeLog; release history is maintained in
NEWS.md only.DESCRIPTION: LazyData: true (replacing
LazyLoad).xtable() from xtable; added
man/xtable.Rd.R/tukeyc-utils.R for nested
filters, emmeans CI columns, error-term renaming, and
interaction labels; removed eval(parse()) from nest/boxplot
code paths.TukeyC.lm() and make.TukeyC.groups():
ifelse() side effects replaced with if
blocks.doBy,
parallel).testthat coverage
(test-tukeyc-extra.R: groups, boxplot, FE nest, xtable
export).R/ translated to English; grammar and spelling corrected in
man/, demo/, and README.md
(user-facing text and examples).doBy package.
doBy::LSmeans produced unwanted side-effects in the console
and in Sweave/knitr documents.emmeans package as a dependency.emmeans.mtext call that was incorrectly placed outside
the scope of the axis1 argument.xtable.TukeyC.Rd.LSmeans object, replaced
aux_mt$coef[,1] with
with(aux_mt, estimate).boxplot.TukeyC and plot.TukeyC,
replaced par(mar = op) with
on.exit(par(mar = np)) to restore graphics parameters
reliably.axis1 and axis2 to the
plot function, giving users greater flexibility to
customise their own axes.TukeyC.lmerMod: corrected the calculation
of MSE and dfr.TukeyC.lmerMod, TukeyC.lm,
and TukeyC.aovlist: substituted levelss with
aux_MSE for split-plot and split-split-plot designs.plot.TukeyC and
boxplot.TukeyC: in plot.TukeyC, changed
names(x$out$Result[,1]) to
row.names(x$out$Result); in boxplot.TukeyC,
added treat <- 'treat'.m.infos.lmerMod: corrected the degrees of
freedom column used for confidence intervals
(aux_mt$coef[,3] → aux_mt$coef[,4]).xtable.TukeyC method and corresponding
documentation.boxplot.TukeyC.Rd.TukeyC.Rd, plot.TukeyC.Rd,
and boxplot.TukeyC.Rd.NAMESPACE adjustment.boxplot.TukeyC method.make.TukeyC.groups that caused an infinite
loop with severely unbalanced data.make.TukeyC.groups was replaced.parallel package as an import (later removed
for CRAN policy).make.TukeyC.test: vece
object now uses as.vector(MSE).lme4 and pbkrtest packages to
Suggests.TukeyC.nest.aovlist.TukeyC.lmerMod method.lme4 to Imports in
DESCRIPTION (later moved to Suggests).ci (confidence interval) and cip
(pooled confidence interval) dispersion options to
plot.TukeyC.match.call() internally to TukeyC.lm
to retrieve arguments.adjusted.pvalue argument to
TukeyC.print.TukeyC,
TukeyC.formula, and TukeyC.lm.TukeyC.aov with TukeyC.lm.m.inf.1a, m.inf.1b,
m.inf.2a, m.inf.2b, m.inf.3a, and
m.inf.3b with m.infos.lm,
m.infos.aovlist, m.infos.nest.lm, and
m.infos.nest.aovlist.dispersion argument from
TukeyC and added it to plot.TukeyC.nest.lm and TukeyC.nest.aovlist are
now internal functions.TukeyC.nest functions were optimised.doBy package as a dependency (replaced by
emmeans in 1.3-44).DESCRIPTION.cv function to calculate the coefficient of
variation for lm, aov, and
aovlist objects.model.frame.aovlist method with calls to the generic, to
meet CRAN requirements.TukeyC.nest.aovlist.R: occurrences of
[:punct:] (incorrect) replaced with
[[:punct:]] (correct).SPET (Split-plot in time).Differences of the returned list was renamed
to Diff_Prob. The upper triangle of the matrix stores the
differences between means and the lower triangle stores the respective
Tukey-test p-values.These binaries (installable software) and packages are in development.
They may not be fully stable and should be used with caution. We make no claims about them.
Health stats visible at Monitor.