NEWS.md

biometryassist 1.5.0

Major changes

• multiple_comparisons(): the plot, label_height, rotation, save, and savename arguments are now deprecated and will be removed in a future version. Use autoplot(<result>) for plotting (pass label_height and rotation there), and write.csv(result$predictions, "file.csv") for saving. The pred, order, and pred.obj arguments were deprecated in 1.1.0 or earlier and have now been removed.
• multiple_comparisons() gains an adjust argument to choose the p-value adjustment method (any stats::p.adjust() method, in addition to the default Tukey's HSD), and a by argument to run comparisons independently within groups.
• Added support for aovlist and nlme::lme() models in multiple_comparisons() (#107).
• Broadened model-engine support across both workflows to bring resplot() and the comparison functions (multiple_comparisons(), pairwise_comparisons(), reference_comparisons()) closer to parity:
  • The comparison functions now support afex (afex_aov), glmmTMB, and sommer's mmes() models. glmmTMB predictions are on the link scale with asymptotic degrees of freedom (supply trans to back-transform); sommer mmes() predictions and SEDs come from sommer's native predict(), also with asymptotic degrees of freedom.
  • resplot() now supports multi-stratum aov models fitted with Error() (aovlist, one panel per error stratum), afex_aov models, and Gaussian-family glmmTMB models.
  • lme4breeding::lmebreed() (relationship-based mixed) models are supported by both workflows: they carry class lmerMod and are handled by the existing lmerMod methods. Comparisons correctly reflect the relationship structure (validated against ASReml-R), using Kenward-Roger degrees of freedom.
  • Deliberate boundaries (with informative errors): ARTool (art) and sommer's legacy mmer models are not available for the comparison functions (ART uses aligned ranks — use ARTool::art.con(); refit mmer with sommer::mmes()), though both remain supported by resplot(). Non-Gaussian glmmTMB models are not valid for resplot()'s normal-Q-Q diagnostic and point to DHARMa::simulateResiduals() instead.
• New function pairwise_comparisons() to test selected pairwise differences (or general linear contrasts) between predicted means, returning a tidy table of estimates, predicted means and multiplicity-adjusted p-values, with a forest plot via autoplot().
• New function reference_comparisons() to compare every level against a single reference (control) level, using an exact Dunnett test by default. It returns a means-centric table (each level's mean, the reference mean and the adjusted difference) and a means plot via autoplot().

Minor changes

• Added the ability to add buffers or double buffers around blocks. (#169)
• autoplot() for multiple_comparisons() output gains several new options (thanks to Michael Mumford, #161): type = "line" joins the means with a line; include_errorbar and include_lettering toggle the error bars and significance letters; errorbar_type = "hsd" draws a single Tukey's HSD reference bar instead of per-mean intervals; and trans_scale = TRUE plots back-transformed means on the model (transformed) scale with an exact back-transformed secondary axis.
• Added a vignette, "Choosing and interpreting multiple comparisons", introducing pairwise_comparisons() and reference_comparisons() alongside multiple_comparisons() and giving guidance on choosing a multiplicity adjustment.

Bug Fixes

• Fixed an issue where asreml doesn't install properly on macOS because the link isn't constructed properly. (#163)
• Fixed Skeletal ANOVA table not showing 2 way interactions for 3 way factorials (#171)
• Colours are now consistent between the output of designs printed with autoplot() and the export_design_to_excel() function. (#170)
• The export_design_to_excel() function is now less fragile. It can handle design objects and data frames as input, and alternative names for the row and column columns. (#168 and #172)
• Fixed a bug where asreml models didn't report the correct number of residual points in resplot(). (#167)

biometryassist 1.4.0

Major changes

• Deprecated des_info(). This function has been superseded by design(), and will be removed in a future version.
• Implement arcsin transformation handling in multiple_comparisons() (#60).
• Demonstrated how to add orientation information to design plots via a vignette (#126).
• Major refactoring of design() in preparation for moving to a new backend later (#102). No user-facing changes.
• Added strip-plot designs (#134).
• Enabled output of p-value matrix from multiple_comparisons(). This required changing the multiple_comparisons() output object to a list, but printing to console and autoplot(<multiple_comparisons>) still work as before (#22).

Minor changes

• Add interval type 'none' for multiple_comparisons() (#125).
• Added a print method for satab() to reliably get the same output (#133).
• Switched from cowplot to patchwork to speed up resplot() (and variogram()) (#29).
• Added and refactored numerous tests throughout to achieve 100% test coverage and speed up tests (#104, #143, #144, #135, #148)
• Added asreml downloads for more operating systems and versions (#158).

Bug Fixes

• Fixed a bug where hex colours don't work with export_design_to_excel() (#124).
• Fixed a bug where buffers weren't added to the plot if they are added after initial design creation (#123).
• Fixed a bug in install_asreml() where it threw an error with more than one new version (#122).
• Fixed a bug where calculate_differences() clashed with package "MuMIn" (#131).

biometryassist 1.3.3

Bug Fixes

• Fixing test issues identified by CRAN after ggplot2 4.0.0 release

biometryassist 1.3.2

Bug Fixes

• Updates to tests and histograms for compatibility with upcoming ggplot2 release.
• Fixed a bug where standard errors that were too small would produce plots with missing upper or lower confidence limits due to rounding the SE to zero. (#119)
• Fixed a bug that made rotated axis labels overlap the plot area (#113)

biometryassist 1.3.1

Bug Fixes

• Update to ensure compatibility with upcoming ggplot2 release (#111)

biometryassist 1.3.0

Major changes

• Switched to using S3 methods for resplot() to enable easier expansion to different models in future. (#100)
• Introduced a new function export_design_to_excel(). An excel file can now be created from a design dataframe, instead of just a graphical plot. (#74)
• Introduced a new comparison interval type in multiple_comparisons(). The new option int.type = 'tukey' will now create comparison intervals using Tukey's distribution rather than a t-distribution for a regular confidence interval. This has been a point of confusion when intervals don't overlap but share letters. (#66)

Minor changes

• Model inputs are now checked for potential transformations that haven't been supplied in multiple_comparisons(). (#83)
• Enabled a verbose option for the quiet parameter in install_asreml() to give more detailed output when required. (#81)
• Added ability to group multiple resplots and variograms into a single grid via a onepage argument. (#73)
• Buffer plots are now implemented within the design data frame, rather than just the plotting logic (#68)

Bug Fixes

• Fixed a bug introduced in v1.2.2 where arguments weren't passed through properly to asreml. (#98)
• Fixed a bug which broke the messages about deprecated parameters in resplot. (#97)
• Fixed a long-standing bug where logl_test would work if random terms were given in resid. (#7)

biometryassist 1.2.2

Major changes

• Switched to using S3 methods to get predictions in multiple_comparisons() to enable easier expansion to different models in future. (#92)

Minor changes

• Added ability to produce column plots from multiple_comparisons() (#90)
• Add option in multiple_comparisons() to disable letter comparisons (#85)
• Enable custom colour palettes for design plots (#84)

Bug Fixes

• Fixed CRAN warnings due to changes in the sommer package (#89)
• Fixed errors in shapiro.test() within resplot() with too many data points (#87)
• Fixed a bug where heat_map() didn't work properly with factor columns (#86)
• Split-plot design dataframe doesn't have the required columns (#82)

biometryassist 1.2.1

Bug Fixes

• The new summary_graph() function was accidentally left out of the CRAN submission.

biometryassist 1.2.0

Major changes

• Introduced the summary_graph() (#75) and heat_map() (#19) functions
• Enabled arbitrary row, column, block and treatment columns to be provided in the autoplot.design() function, to enable more general plotting of designs. (#28)

Minor changes

• Implemented the ability to plot designs with buffer plots. (#68)
• Changed install_asreml() to check if there is a later version before downloading.
• Enabled non-standard evaluation input of column names in autoplot.design().

biometryassist 1.1.3

Bug fixes

• Better checking of column names in data provided to multiple_comparisons() to prevent breaking. (#53)
• Updated install_asreml() to work with ARM chip macOS devices. (#54)
• Wrote a vignette with instructions for installing ASReml-R. (#55)
• Fixed variogram to enable it to work with dsum models (i.e. MET models). (#61)

biometryassist 1.1.2

Bug fixes

• Fixed a bug introduced due to a change in names by predictmeans(). (#50)
• Added a check for missing ar1() component in variogram(). (#49)
• Added an error check for terms provided in the wrong order to multiple_comparisons() via classify. (#48)
• Checked if model needs the present argument passed to predict.asreml(). (#41)

biometryassist 1.1.1

Minor changes

• multiple_comparisons() now accepts power transformations and automatically back-transforms. It gains a new argument power to provide the transformation power applied in the model to undo. This enables more general Box-Cox transformations. (#36)
• multiple_comparisons() no longer produces an error when the trans argument is supplied and offset is not. It now produces a warning and sets offset to 0 when not provided. (#37)
• Added an option to turn off the start up message and version check. Add options(biometryassist.check = FALSE) to your .Rprofile file to disable. Partially fixes #6.
• Enabled new colour-blind friendly palettes (#39)

Bug fixes

• Updated the required version of rlang (>=1.0.0)
• Fixed a bug that didn't allow labels and the x axis to be rotated independently for autoplot.mct() (#35)
• Fixed an issue where treatment columns were not determined correctly in multiple_comparisons() (#33)
• Fixed a problem with variograms displaying grey values where NAs have been produced. (#24 and #25)
• Fixed some warnings that would be introduced with the forthcoming version of ggplot2 (#42)

biometryassist 1.1.0

Major changes

• multiple_comparisons() no longer requires calls to predict.asreml() to be passed into the function, as the predicted values are now calculated internally. Additional arguments can be passed to predict.asreml() via the ... argument. (#27)

Minor changes

• The order argument of multiple_comparisons() has been deprecated in favour of a new argument descending. This takes logical (TRUE or FALSE) values only, so default is no longer possible as it was producing incorrect results. (#8)
• resplt() has been deprecated in favour of resplot() and will be removed in a future version (#20).
• Warnings about lack of convergence are no longer output in logl_test(). (#17)

Bug fixes

• Aliased levels are printed properly in multiple_comparisons() now. (#14)
• R.param and G.param are removed from the asreml() call on resplot() if not explicitly provided. (#21)
• Fixed a bug where install_asreml() would not work on macOS Monterey. (#16)

biometryassist 1.0.0

Minor changes

• mct.out() has been renamed to multiple_comparisons()
• logl.test() has been renamed to logl_test()
• des.info() has been renamed to des_info()

Previous versions

For changes prior to biometryassist 1.0.0 see the BiometryTraining package at https://biometryhub.github.io/BiometryTraining/news/index.html.