Na minha versão da multicomp no Ubuntu 16.04 com R não deu warnings. > modeloPARSUBlme <- lme(PRODLEIT ~ BLOCO + PASTO * MINERAL, + random = ~1 | PARCELA, + data = PARCSUB) > > compara <- glht(modeloPARSUBlme, linfct = mcp(PASTO = "Tukey")) Warning message: In mcp2matrix(model, linfct = linfct) : covariate interactions found -- default contrast might be inappropriate > summary(compara)
Simultaneous Tests for General Linear Hypotheses Multiple Comparisons of Means: Tukey Contrasts Fit: lme.formula(fixed = PRODLEIT ~ BLOCO + PASTO * MINERAL, data = PARCSUB, random = ~1 | PARCELA) Linear Hypotheses: Estimate Std. Error z value Pr(>|z|) 2 - 1 == 0 0.3333 1.4829 0.225 0.99600 3 - 1 == 0 1.0000 1.4829 0.674 0.90684 4 - 1 == 0 4.6667 1.4829 3.147 0.00899 ** 3 - 2 == 0 0.6667 1.4829 0.450 0.96973 4 - 2 == 0 4.3333 1.4829 2.922 0.01821 * 4 - 3 == 0 3.6667 1.4829 2.473 0.06416 . --- Signif. codes: 0 ‘***’ 0.001 ‘**’ 0.01 ‘*’ 0.05 ‘.’ 0.1 ‘ ’ 1 (Adjusted p values reported -- single-step method) > > packageVersion("multcomp") [1] ‘1.4.6’ > R.version.string [1] "R version 3.3.1 (2016-06-21)" > > browseURL("https://cran.r-project.org/web/packages/multcomp/index.html") À disposição. Walmes.
_______________________________________________ R-br mailing list R-br@listas.c3sl.ufpr.br https://listas.inf.ufpr.br/cgi-bin/mailman/listinfo/r-br Leia o guia de postagem (http://www.leg.ufpr.br/r-br-guia) e forne�a c�digo m�nimo reproduz�vel.