Changes in version 0.9-83-12 (2025-07-15) o small change in rating.emmeans (thanks to Russell Lenth) Changes in version 0.9-83-11 (2025-04-22) o adonis.II changed to build on adonis2 rather than adonis (package vegan) (thanks to Jari Oksanen) Changes in version 0.9-83-7 (2023-11-06) o MVA.plot corrected for a minor issue (thanks to Morgane Ourry) Changes in version 0.9-83-3 (2023-09-26) o small technical changes following CRAN request Changes in version 0.9-83-2 (2023-08-23) o small technical changes following CRAN request Changes in version 0.9-83 (2023-06-14) o Anova.clmm corrected to adapt to the model.matrix method now in the ordinal package (thanks to Henning Pohl) NA Changes in version 0.9-82-2 (2023-05-11) o fp.test changed to implement the original version of the Fligner-Policello test o pcor (then pcor.test) changed to implement a more relevant method to compute Spearman's partial correlation coefficients (thanks to Dave Markowitz and Seongho Kim) o Anova.clm and Anova.clmm corrected for a typo in results of type III tests (thanks to Su Shen) o small technical changes following CRAN request Changes in version 0.9-81-2 (2022-02-21) o small technical changes following CRAN request Changes in version 0.9-81 (2021-12-14) o perm.anova corrected for an error in p-value reporting with some specific designs (thanks to Carlos Rivera Moreno) o plotresid extended to betareg and glmmTMB models o new function p.beta for rescaling of a [0,1] variable into the (0,1) interval (and vice-versa) o new transformation 'p.beta' in back.emmeans (inverse of the scaling performed by p.beta) o new functions quasibinomial.QAIC and quasipoisson.QAIC to allow calculation of QAIC(c) with GLMs of the quasi- family Changes in version 0.9-80 (2021-06-28) o fisher.bintest corrected for changing the p-value adjustment method with pairwise comparisons Changes in version 0.9-79 (2021-01-27) o predict.least.rect now returns fitted values if 'newdata' omitted Changes in version 0.9-78 (2020-09-04) o perm.anova corrected for printing problems with R version 4 Changes in version 0.9-77 (2020-06-15) o test.multinom corrected for a small bug o new function elogis (empirical logit link) for quasi-logistic models Changes in version 0.9-75 (2020-03-04) o small technical changes following CRAN request Changes in version 0.9-74 (2020-01-07) o MVA.plot now uses the same default scale for x and y axes o pairwise.perm.manova can now return F values and R2 values o new functions multtest.gp.bin (and associated plotting method) for univariate comparison of groups for multiple binary variables o CvM.test removed (the cramer.test function of the package cramer does the same job) o new argument 'col' in byf.hist Changes in version 0.9-73 (2019-03-26) o new argument 'type.DA' in predict.MVA.cv and predict.MVA.cmv (probability for the most probable class or for each class) o new argument 'type' in predict.CDA.cv (probability for the most probable class or for each class) Changes in version 0.9-72 (2019-02-11) o MVA.cv and MVA.cmv improved to return individual prediction probabilities o MVA.cor corrected for PCIA and CIA based on at least one mix analysis o MVA.scores, MVA.cor and MVA.load improved to return more than 2 axes o fourth-root transformation added to multtest.gp Changes in version 0.9-71 (2019-01-11) o least.rect() corrected for >2 levels (printing error) o MVA.cv and MVA.cmv improved to return confusion matrices Changes in version 0.9-70 (2018-11-06) o dunn.test removed (the dunnTest function of the package FSA does the same job) o pairwise.to.groups removed (not very useful) o package dependencies changed to follow migration of mixOmics from CRAN to Bioconductor Changes in version 0.9-69-3 (2018-05-14) o changes in help pages as requested by CRAN Changes in version 0.9-69-2 o cochran.qtest corrected for pairwise comparisons with identical groups (thanks to Duncan Hedderley) Changes in version 0.9-69 (2018-01-05) o OR.multinom and test.multinom corrected for two-level responses o change from package 'lsmeans' to 'emmeans': back.lsmeans becomes back.emmeans, rating.lsmeans becomes rating.emmeans o plotresid improved to deal more properly with "quasi" distributions in GLM(M)s Changes in version 0.9-68 (2017-08-21) o miscellaneous small improvements Changes in version 0.9-66 (2017-07-10) o argument thresh of MVA.corplot improved o few linguistic improvements Changes in version 0.9-65 (2017-05-03) o MVA.synt extended to DIABLO o MVA.scores, MVA.cor, MVA.load (hence MVA.plot) extended to DIABLO o new function DIABLO.cv (cross validation for DIABLO) o new function DIABLO.test (significance test for DIABLO) Changes in version 0.9-64 (2017-03-25) o plotresid extended to glmmPQL models o new function pairwise.var.test (pairwise comparisons based on F-tests) o new function pairwise.perm.var.test (pairwise comparisons based on permutational F-tests) Changes in version 0.9-63 (2017-02-24) o back.lsmeans corrected for log transformations, fourth-root transformation added o MVA.plot adapted for GPA o plotresid re-thought Changes in version 0.9-62 (2016-12-13) o se corrected for proportions Changes in version 0.9-61 (2016-10-31) o MVA.cv and MVA.cmv corrected for errors provoked by scaling with nearly constant variables Changes in version 0.9-60 (2016-08-20) o MVA.synt extended to MCA, mix analysis, GPA, 2B-PLS, CCorA, rCCorA, RGCCA, CIA and PCIA o MVA.corplot extended to db-RDA o new function stand (standardization of a data frame based on another data frame) o intergroup variance removed from MVA.synt (not relevant) o new function CDA.cv (cross validation for CDA) o new predict methods for "CDA.cv" objects o new function CDA.test (significance test for CDA) o new function pairwise.CDA.test (pairwise comparisons for CDA) o pairwise.factorfit corrected for CA and CCA computed with the vegan package o new function to.dudi (conversion of some vegan analyses to ade4 format) o MVA.scores (hence MVA.plot) extended to (Generalized) Procrustean superimposition o MVA.cor (hence MVA.plot) extended to Generalized Procrustean superimposition o new function GPA.test (significance test for GPA) o new function cov.test (significance test for covariance) o new function ord.rw (re-computation of an ordination using given row weights) Changes in version 0.9-57 (2016-07-14) o new function pairwise.factorfit (pairwise comparisons of groups displayed on a factorial map) o MVA.anova extended to deal with partial CCA/RDA/db-RDA o MVA.synt extended to db-RDA o new argument 'correct' in chisq.bintest (continuity correction) o new argument 'y' in se (standard error of a proportion) o new function cdf.discrete (Cumulative Distribution Function of a known discrete distribution) o prop.multinom corrected for 1-row matrices o new function wald.ptheo.multinom.test (Wald tests for comparison of proportions to theoretical values) o multinomial.test, multinomial.multcomp and multinomial.theo.multcomp accept factors as response o new argument 'prop' in multinomial.theo.multcomp (results displayed as counts or proportions) o new function dunn.test (Dunn's test) NA o new argument 'progress' in all function performing permutation tests (display of the progress bar) o new argument 'scale' in MVA.cv, MVA.cmv and MVA.test (scaling) o new function pairwise.MVA.test (pairwise comparisons based on cross (model) validation) o new function cond.multinom (condition number of the Hessian matrix of a multinomial log-linear model) o new function OR.multinom (odds ratios in multinomial regression) o new function test.multinom (significance test in multinomial regression) Changes in version 0.9-56 (2016-06-06) o MVA.synt extended to COA, RDA, CCA o new argument 'vars' in multtest.gp and plotting method optimized o splitf, MVA.cv, MVA.cmv, MVA.test optimized Changes in version 0.9-55 (2016-04-23) o function multtest renamed multtest.gp o new function multtest.cor (correlation test for multiple variables) o new function loc.slp (slope of a hand-defined line) o new function coord.proj (coordinates of projected points) o functions MVA.scores, MVA.cor and MVA.load are now visible Changes in version 0.9-54 (2016-03-28) o small bugs corrected in MVA.plot o new argument 'adj' in least.rect (correction of confidence intervals and p-values for multiple testing) o new function spearman.cor.multcomp (computation of adjusted confidence interval of Spearman's correlation coefficients for multiple comparisons) o small bug corrected in prop.multinom o new function dummy (creation of dummy responses from a factor) Changes in version 0.9-53 (2016-02-28) o small bugs corrected in MVA.synt o new function multtest (univariate comparison of groups for multiple variables) Changes in version 0.9-52 (2015-11-15) o small bugs corrected in MVA.plot Changes in version 0.9-51 (2015-10-18) o small bugs corrected in MVA.plot o plotresid rewritten, new support for gls models o new arguments xlab and ylab in byf.hist Changes in version 0.9-50 (2015-08-08) o wald.ptheo.test now deals with overdispersion o new function prop.multinom (computation of proportions and SE based on a multinomial log-linear model) o new function wmean (weighted arithmetic mean) o plot1comp.ind, plot1comp.var, s.corcircle2, scat.mix.categorical, scat.mix.numeric and scatter.coa2 removed (the MVA.plot function of this package does the same job and is more generic) o new function splitf (random splitting of data frame, respecting the relative proportions of levels of a factor) o new function MVA.cmv (cross model validation) o new function MVA.cv (cross validation) o DA.confusion and DA.valid removed (the MVA.cmv and MVA.cv functions of this package do the same job and are more generic) o new predict methods for "MVA.cv" and "MVA.cmv" objects o new function MVA.test (significance test based on cross (model) validation) o PLSDA.test removed (the MVA.test function of this package does the same job and is more generic) o PLSDA.ncomp removed (not really useful and the mvr function of the 'pls' package does nearly the same job) o new function MVA.plot (various plots for multivariate analyses) o cor.sparse removed (the MVA.plot function of this package does the same job and is more generic) o LDA.format not exported anymore (the MVA.plot function of this package does the same job and is more generic) o new arguments 'ord' and 'decreasing' in back.lsmeans o new function MVA.anova (wrapper to anova.cca of the 'vegan' package but for type II tests) o perm.t.test corrected for the computation of p-values (underestimated in some particular cases when using a two tailed test) o MVA.synt rewritten Changes in version 0.9-45 o histograms with density polygons improved o G.test, G.multcomp and G.theo.multcomp modified to deal with 0 values (but warning that it should not be done) o new functions multinomial.test, multinomial.multcomp and multinomial.theo.multcomp (exact multinomial goodness-of-fit test and pairwise comparisons) o chisq.bintest splitted into chisq.bintest and fisher.bintest (chi-square and Fisher's exact tests for comparing response probabilities) o new function G.bintest (G test for comparing response probabilities) o new functions chisq.theo.bintest, chisq.bin.exp and prop.bin.multcomp (comparison of response probabilities to theoretical values) o new function fp.test (Fligner-Policello test) o new function CvM.test (two-sample Cramer-von Mises test) o new method for perm.t.test o new method for perm.var.test o new functions pcor and pcor.test (equivalents to cor and cor.test for (semi-)partial correlation) o new function pairwise.to.groups (conversion of a pairwise-comparison matrix to letters showing significantly different factor levels) o "mlm" models are now dealt properly by plotresid o pairwise.manova removed (dealt in a much powerful manner by the 'lsmeans' package) o new function pairwise.perm.manova (pairwise comparisons using permutational MANOVAs) o wald.ptheo.test accepts 2-column matrices as response o new function adonis.II (wrapper to adonis of the 'vegan' package but for type II tests) o new predict method for "coadisc" objects (Correspondence Discriminant Analysis performed with discrimin.coa from 'ade4') o DA.valid and DA.confusion can now handle "coadisc" objects (Correspondence Discriminant Analysis performed with discrimin.coa from 'ade4') o new arguments arrows in s.corcircle2 o new function scat.cr ("correlation" of variables to axes in MCA or mix analyses) o MVA.synt extended to NSCA o wilcox.signtest now computes the confidence interval of the Hodges-Lehmann estimator (and this estimator) o new functions mood.medtest (Mood's median test) and pairwise.mood.medtest o new function prop.multinom.test (pairwise comparisons of proportions based on multinomial log-linear models) o wilcox.rating.signtest, wilcox.rating.test, kruskal.rating.test, friedman.rating.test, pairwise.wilcox.rating.test and wilcox.paired.rating.multcomp removed (these tests can be problematic with ratings, CLMs (package 'ordinal') are much better) o new function back.lsmeans (back-transformation of LSMeans and SE interval) Changes in version 0.9-41 (2014-11-15) o lsm.basis.clm and lsm.basis.clmm removed (now dealt in a much powerful manner by the 'lsmeans' package) o DA.var removed (the MVA.synt function of this package does the same job and is more generic) o fc.multcomp removed (comparison of slopes dealt in a much powerful manner by the 'lsmeans' package) o plot1comp.ind rewritten to display a more easy-to-interpret graph o byf.normhist removed (not very useful and nearly same thing now done by byf.hist) o MVA.synt extended to MCA and mixed analyses