| news | R Documentation |
Rebuild the vignettes prior to CRAN submission.
Add envir argument to getFormulae.asreml and printFormulae.asreml to make them more robust to where the objects in the asreml.obj have been defined.
Fix bug in getFormulae.asreml and printFormulae.asreml that occurs when formula(e) have been supplied to asreml in an object.
Change the Maintainer email address.
Add ellipsis to as.asrtests call within an rmboundary.asrtests call so that arguments in the calling routine are passed through.
Add a trap in recalcWaldTab.asrtests for a NULL wald.tab before dealing with denDF so that recalcWaldTab.asrtests throws a warning rather than an error.
Modify recalcWaldTab.asrtests to deal with a Wald table that has Chi-square instead of F statistics (this happens when denDF = "none".)
Increment version number for resubmission to CRAN.
Fix bug in changeTerms when both addFixed and dropFixed are NULL.
Revisions to the manual.
Fix bug in forming test.summary.
Added the IClikelihood argument to chooseModel.asrtests, reparamSigDevn.asrtests, rmboundary.asrtests, testranfix.asrtests, testresidual.asrtests, and testswapran.asrtests.
Fix bug in printFormulae when the formula is long.
Various bug fixes associated with asreml-R version 3.
Fix bug in processing a formula that includes an at function.
Removed the material.diff argument and the both option from the which.IC argument of changeModelOnIC.
Change likelihood in infoCriteria to IClikelihood to make it consistent with other functions.
Replace tol.diff with material.diff and set the default to 0.5 in changeModelOnIC.
Revise all vignettes.
Add a new vignette for the use of information criteria with the wheat experiment.
Fixed bugs in changeModelOnIC associated with addFixed and dropFixed and with dealing with unconverged models.
This version represents a major revision in that the facilities for employing information criteria (AIC and BIC) have been considerabley expanded. The infoCriteria method has been modified to add the possibility of calculating not only the the information criteria based on the REML likelihood, but those based on the full likelihood instead. There are now two infoCriteria methods, one for asreml objects and the other for lists of asreml objects. An alternative is to use changeTerms.asrtests wiith IClikelihood set to REML or full and the information criteria will be included in the The test.summary of the asrtest object. A new function changeModelOnIC has been included to allow model selection to be based on the information criteria, rather than on hypothesis tests. However, the two methods of selecting models can be interweaved.
Add argument omit.columns to print.test.summary that allows the specification of columns to be omitted from the printout.
Various modifications to the internal code for the handling of the test.summary component of an asrtest.object to allow more flexibility in the make up of test.summary.
Add function iterate.asrtests to execute additional iterations of the fit stored in an asreml.obj within an asrtests object; the model itself cannot be changed.
Add functions getFormulae.asreml and printFormulae.asreml to extract and print the formulae stored in the call of an asreml object.
Add trace argument to newfit.asreml and activated it for asreml-R version 4.
Made R >= 3.5.0 a requirement for asremlPlus.
Add chooseModel.data.frame function.
Modify linTransform.alldiffs so that submodels involving covariates are possible.
Add print.test.summary function
Split Ladybird vignette into two, one based on asreml and the other on lm, lmerTest and emmeans.
Modified newfit to circumvent problems in the test functions in dealing with terms that include the at function and modified testranfix to improve its detection of multiple terms.
Correct date in DESCRIPTION for CRAN rsubmission.
Rebuild for CRAN submission.
Change default for subset argument in subset.alldiffs so that the complete set of predictions is returned. Also, change check on the resulting classify so that it checks whether the variables in the classify uniquely index the predictions.
Include in renewClassify.alldiffs a check that the newclassify uniquely indexes the predictions.
Add printPlot = FALSE to both plotPvalues.data.frame and plotPvalues.alldiffs. Change return for plotPvalues.data.frame from nothing to the plot produced using ggplot.
Fix bug in check for predict.asreml returning sed and/or vcov when requested.
Add new functions facRecode.alldiffs and facRename.alldiffs.
Implement a check that predict.asreml has returned sed and/or vcov when requested.
Allow for calculation of notional LSDs when LSDs for a single observation are specified.
Removed restriction that overall LSD is always used when the range of the SEDs divided by the average of the SEDs is less than the avsed.tolerance.
A bug in detecting valid wald.tab objects was fixed.
Modify testranfix.asrtests, as.asrtests, recalcWaldTab.asrtests and chooseModel.asrtests to allow for p-values based on a conditional Wald F-statistic if one is present in the wald.tab.
Allow for 6-column wald.tab such as is obtained for ssType set to "conditional".
Revise Wheat vignette to use qqplotr for Normal Probability Plots.
Revise test for tilde (~) in formula supplied to changeTerms so that only a leading tilde causes an error.
Rebuild for R 3.6.0.
Fix a bug in changeTerms.asrtests that reset the residual model to the default when changing fixed or random terms.
Check for NULL wald.tab when setting its class prior to storing it in an asrtests.object.
Add function addBacktransforms.alldiffs.
Allow numerics, in addition to factors, in LSDby argument of predictPlus.
Rename reorderClassify to renewClassify.
Fix a bug in retention of attributes of the alldiffs.object in renewClassify.
Add transform.power, offset and scale as attributes of the backtransforms component of an alldiffs.object.
Rework the storage of the backtransforms component of an alldiffs.object to ensure that it is retained when manipulating alldiffs.object.
Build in R version 3.5.3.
Update the Author field of the DESCRIPTION to include an ORCID.
Allow backtransformed halfLSD intervals in the backtransforms component of an alldiffs.object.
Build in R version 3.5.2.
Update the license to remove blank line and resubmit to CRAN.
Build in R version 3.5.2.
Update the license to include 2019.
Add print.predictions.frame and print.wald.tab as S3 methods to give more control over the printing of objects of class wald.tab and predictions.frame.
Made sure that class wald.tab is associated with a wald.tab and classes asreml.predict and predictions.frame are associated with a predictions.frame when these are produced by asreml.
Add colourise argument to print.alldiffs so that the default is FALSE and it overrides the asreml.options setting.
Use R.rsp to install vignettes so that hyperlinks are active.
Add colourise argument to print.asrtests so that the default is FALSE and it overrides the asreml.options setting.
Fix bug in infoCriteria.asreml when DF supplied. For both infoCriteria.asreml and REMLRT.asreml, calculate the bound terms and if appropriate give arning messages.
More vignettes changes, including adding manual to vignettes.
Fix accidental reordering of alldiffs object when meanLSD.type is factor combinatons.
Make vignettes visible.
Modify estimateV in response to correction of corb naming in latest build.
Revise Wheat vignette and entry in asremlPlus-package documentation.
Add Ladybird predictions vignette.
Modify printing of wald.tab by print.asrtests to remove colouring because it causes problems with knitr.
Add a check to plotPredictions.data.frame to warn when linear.transformation is supplied.
Also remove zero LSDs when calculating overall LSD and sed.range.
Add a check to linTransform.alldiffs that factors in LSDby are in the submodel.
Add the Wheat example as a vignette.
Remove LSDs for which sed is effectively zero from the calculation of LSD statistics, provided not all are zero.
Fix bug in test of the range of SEDs against avsed.tolerance when caclulating LSDs.
Add attributes meanLSD.type and LSDby to alldiffs objects so that redoErrorIntervals.alldiffs can determine these attributes when its meanLSD.type argument is not set.
Add function getTestPvalue.asrtests.
Minor documentation changes.
Add entries for predictions.frame, alldiffs.object and asrtests.object and made changes to the documentation to provide links to these pages.
Defined classes alldiffs, asrtests and predictions.frame.
Added the functions is.alldiffs, validAlldiffs, is.asrtests, validAsrtests, is.predictions.frame and validPredictionsFrame for validating the objects.
Added tests for the validity of objects to methods functions.
Provided as.asrtests function, while retaining asrtests function as a pseudonym for as.asrtests. Added as.prediction.frame function.
Add examples for alldiffs and data.frame methods functions that use lme4 to show how to use asremlPlus with packages othere than asreml.
Correct predictPlus, plotPredictions and allDifferences.dat.frame to deal with a classify equal to "(Intercept)".
Implement fix of R.param and G.param in supplied object for corb in estimateV function.
Make documentation changes for asreml-R4.1.
Add Ladybird.dat data set.
Fix minor bugs in redoErrorIntervals.alldiffs.
Allow no Vmatrix in linTransform.alldiffs when error.intervals is none and allow transformation of predicted.value only when vcov component of alldiffs object is not available.
Allow no sed in allDifferences.data.frame when not pairwise is TRUE.
Modify legend size and position in plotPvalues.alldiffs.
Add new function reorderClassify.alldiffs.
Add rmClassifyVars to subset.alldiffs.
Rebuild under latest version of R 3.5.0 with requirement for R >= 3.1.0.
Fix bug in bootREMLRT.
Changes to make asremlPlus with the release version of asreml version 4.1.
Add new functions getASRemlVersionLoaded and loadASRemlVersion to facilitate handling of different versions of asreml.
Fixed bug in predictPlus that meant the denominator degrees of freedom could not be obtained from wald.tab when error.intervals was set to "none" or "StandardError".
Fixed bug in LSDby option that meant the correct subsets were not being identified when the levels of one factor in the predictions are subset of another factor.
Add new function facCombine.alldiffs.
Fix minor bug in plotPvalues.alldiffs associated with factors.per.grid when there ais more than one factor indexing the different grids.
Add new function facCombine.alldiffs.
Add factors.per.grid plotPvalues.alldiffs to allow automatic calculation of grid spacing.
Add argument linear.transformation to predictPresent.
Minor bug fix in print.alldiffs.
Add argument vcov to allDifferences.data.frame and as.alldiffs and modify print.alldiffs, recalcLSD.alldiffs, sort.alldiffs and subset.alldiffs to process the vcov component of an alldiffs object.
Add argument linear.transformation to predictPlus to enable a linear transformation of the predictiions as specified by a matrix or a model formula.
Add function linTransform.alldiffs that effects a linear transformation of the predictions stored in an alldiffs object.
Fixed bug in backtransforming predictions in predictPlus when offset is nonzero and scale is not one.
Fix bug in gridline in plotPvalues whentriangles is set to upper or lower.
Fix bug in reordering components of an alldiffs object.
Change license to MIT.
Modifications to checking of options for function arguments.
Add tip for installing asremlPlus from github.
Modifications to internals.
Fix bug in redoErrorIntervals.alldiffs to make sure status or est.status is the last column in the predictions component of the alldiffs object.
Modifications to internals.
Add colours argument to plotPvalues.data.frame and to plotPvalues.alldiffs and add triangles argument to plotPvalues.alldiffs. In plotPvalues.data.frame, move legend.position to bottom of plot and increase legend.width to 2 cm. Also, remove panel.grid from plot and enforce an aspect.ratio of one.
Fix bug in subset.asreml that did not reduce the levels of the in the prediction component of an alldiffs object to those remaining after subsetting.
Rebuild the package under the latest version of R.
Add code to allDifferences.data.frame that ensures that the order of the predictions, and associated compoenents are in standard order for the classify on which the predictions are based.
Add subset.alldiffs function.
Fix bug in REMLRT.asreml related to bound.exclusions with asreml3.
Build under the latest version of R.
Have modified testresidual.asrtests, testranfix.asrtests and testswapran.asrtests to fit the new random/residual model when the old random/residual model has not converged and allow.unconverged is set to FALSE. In such cases the value of p will be NA. For these functions, when airthe the new or the old model has failed to converge, an indication of failure to converge will be added to the action reported in test.summary.
Modified meanLSD.type argument in allDifferences.data.frame, predictPlus.asreml and predictPresent.asreml to include a factor.combinations option that obtains the mean LSD for each combinaton of the levels of one or more factors.
Added functions recalcLSD.alldiffs and redoErrorIntervals.alldiffs to enable recalculations on alldiffs objects.
(Added call to asreml.options with keep.order = TRUE in newfit.asreml when asreml4 is loaded, because asreml4 requires it.)
Modified recalcWaldTab.asrtests to pass empty wald.tab when wald.asreml has failed.
Made minor changes to testresidual.asrtests to make clear the still use rcov in asreml3.
Fixed bug in REMLRT.asreml and rmboundary.asrtests.
Fixed bugs in allDifferences.data.frame and plotPvalues.alldiffs.
Compiled with the latest version of R
Some internal recoding to replace calls to summary.asreml.
Added gridspacing option to plotPvalues.alldiffs and plotPvalues.data.frame so that a grid could be formed over groups of rows and columns“.
Added function sort.alldiffs to sort the components of an alldiffs object according to the predicted values. Add arguments and a call to it to predictPlus.asreml, predictPresent.asreml and plotPvalues.alldiffs.
Added attributes sortFactor and sortOrder to an alldiffs object so that this is accessible to users for use in other calls.
Added the oats split-plot design from Yates (1937).
Minor change to as.alldiffs to make sure that using standard.error and est.status rather than std.error and status in the predictions data.frame.
Added which.matrix argument to estimateV so that could estimate the varaince, random or residual matrix.
Incorporate newresidual.asrtests into changeTerms.asrtests and added check for boundary and singular terms.
Added checkboundaryonly argument to rmboundary.asrtest and all functions that call it so that could control removal of boundary and singular terms.
Incorporate newresidual.asrtests into changeTerms.asrtests and added check for boundary and singular terms.
Change full.asreml.obj and reduced.asreml.obj to h1.asreml.obj and h0.asreml.obj in REMLRT.asreml and reordered them.
Add function bootREMLRT.asreml and replace addrm.terms.asrtests with changeTerms.asrtests.
Make the default in variofaces.asreml for V be NULL, in which case V is obtained using estimateV.asreml.
Fix bug in plotPvalues arising from asreml not always returning factors in the predicted values.
Modify varofaces.asreml and simulate.asreml to perform the simulations and analysis of data sets using parallel processng.
Add recalcWaldTab to asrtests so that wald.tab options for denominator degrees of freedom are taken into account whenever wald.tab is recalculated.
Add arguments DF and bound.exclusions to REMLRT.asreml and infoCriteria.asreml to allow more control over how the DF are determined. The number of bound parameters was added to the data.frame produced by these methods. Also, the arguments bound.exclusions and REMLDF were added to the methods testranfix.asrtests, testresidual.asrtests and testswapran.asrtests.
Added meanLSD.type to allDifferences.data.frame, predictPlus.asreml and predictPresent.asreml to provide for an overall or per-prediction meanLSD. Allow avsed.tolerance in predictPlus to be set to NA which forces the calculation of LSDs for the overall mean LSD and set calculations of per-prediction LSDs whatever the value of codeavsed.tolerance. Changed to calculate the mean SED to be used for an LSD as the square root of the mean(s) of the variances of pairwise differences.
Added functions plotPvalues.data.frame and plotPvalues.alldiffs to plot heat maps of p-values for pairwise differences between predictions.
Added function estimateV.asreml to form the estimated variance matrix for the observations. However, this function is not available in ASReml-R version 3.
The asremlPlus version 4.x package represents a major revamp of asremlPlus to make it compatible with ASReml-R version 4 and, at the same time, to make the functions that operate on asreml, asrtests and alldiffs objects into S3 methods for these S3 objects. This means that
The function names have been modified so that the only period (‘.’) in the name is that before the object type for which the function is a method;
The object part of the function name is no longer needed when calling the function;
The arguments had to be reordered for some functions so that the argument for the object for which it is a method is the first argument; this may cause problems if matching of arguments by position has been used in calling functions;
The names of some arguments have been changed because of changes in ASReml-R version 4; for example, rcov has been changed to residual throughout.
The full set of changes to function names is detailed in the asremlPlus manual and can be accessed using ?`asremlPlus-deprecated`.
In spite of th changes, the new version still works with ASReml-R version 3, although with changes. A particularly problematic change for version 3 is that testrcov.asrtests becomes testresidual.asrtests even though rcov is still used in calls to asreml.
Version 3 of asremlPlus was skipped in order to line up the version numbers of asreml and asremlPlus.
Add argument allow.unconverged in addrm.terms.asrtests, choose.model.asrtests, newfit.asreml, newrcov.asrtests, sig.devn.reparam.asrtests, testranfix.asreml, testrcov.asrtests, testswapran.asrtests. It allows control over whether an unconverged analysis is to be abandoned.
Rebuild under R 3.4.0.
Added check that wald.tab is a four-column data.frame to predictionplot.asreml and pred.present.asreml.
Added ggplotFuncs argument to predictionplot.asreml and pred.present.asreml.
Added bound.test.parameters to reml.lrt.asreml, choose.model.asartests, testranfix.asrtests, testrcov.asrtests. testwapran.asrtests.
Revised some documentation.
Fixed a minor bug in rmboundary.asrtests.
Fixed some minor bugs in testswapran.asrtests.
Fixed some minor bugs.
Added WaterRunoff.dat data set and modified examples based on this data set so that the examples would run.
Fixed some minor bugs.
Added means argument to variofaces.asreml.
Modifications to predictionplot.asreml and pred.present.asreml as a result of changes made to ggplot2 version 1.0.1.
Added label argument to addrm.terms.asrtests.
Added new function newrcov.asrtests.
Added graphics.device argument to variofaces.asreml and changed default for this argument
to NULL in pred.present.asreml and predictionplot.asreml.
The following functions were deprecated and replaced with functions that have the suffix asrtests instead of asreml, to signify that they operate on asrtests objects: addrm.terms.asreml, choose.model.asreml, recalc.wald.tab.asreml, rmboundary.asreml, sig.devn.reparam.asreml, testranfix.asreml, testrcov.asreml and testswapran.asreml.
The following functions were deprecated info.crit and reml.lrt; they are replaced by info.crit.asreml and reml.lrt.asreml, repsectively.
NEWS and documentation of deprecated functions added.
First version placed on CRAN.