Dados beatriz

---

DATA

database=read.csv("D:/Armazenamento/DATA R/BIA/Data/Acu R.csv")
View(database)
str(database)

'data.frame':   63 obs. of  6 variables:
 $ Trat : chr  "SCT" "SCT" "SCT" "SCT" ...
 $ Ciclo: int  1 1 1 1 1 1 1 1 1 1 ...
 $ Rep  : int  1 2 3 4 1 2 3 4 1 2 ...
 $ CO2  : int  236 269 314 367 375 340 314 359 324 417 ...
 $ N2O  : num  -0.00213 -0.01276 -0.00529 -0.0064 0.00944 ...
 $ CH4  : num  -0.07253 -0.02992 -0.00562 0.00319 -0.0028 ...

database$Trat=as.factor(database$Trat)
database$Ciclo=as.factor(database$Ciclo)
database$CO2=as.numeric(database$CO2)

Lembrar sempre de transformar para fatores os seus tratamentos, e para numerico as suas variaveis respostas.

---

1 - CO2

Outliers

boxplot(database$CO2)

outliers = boxplot(database$CO2)$out 

outliers 

[1] 470

database[which(database$CO2 %in% outliers),] 

O boxplot mostra se existe outlier, a segunda linha mostra qual numero é o outlier e a terceira linha mostra a localização (linha no database) do outlier

Análise de variancia

anova = aov(CO2~Trat*Ciclo, data = database[-12,]) 
summary(anova)

            Df Sum Sq Mean Sq F value   Pr(>F)    
Trat         3  80459   26820  13.650 1.69e-06 ***
Ciclo        3 406515  135505  68.968  < 2e-16 ***
Trat:Ciclo   9  39221    4358   2.218   0.0378 *  
Residuals   46  90379    1965                     
---
Signif. codes:  0 ‘***’ 0.001 ‘**’ 0.01 ‘*’ 0.05 ‘.’ 0.1 ‘ ’ 1

Aquele “-12” no modelo é para desconsiderar a linha com outlier, vc poderia retirar essa linha do data, mas as vezes só é considerado outlier para essa variavel e vc estaria excluindo a linha toda (i.e., não só com os valores de CO2, mas tbm de N2O e CH4), desta forma vc só não considera a lina com outlier e não faz modificações no database.

Análise de pressuposição de normalidade

hist(rstandard(anova))

shapiro.test(rstandard(anova))

    Shapiro-Wilk normality test

data:  rstandard(anova)
W = 0.96994, p-value = 0.1319

Com o histograma e com o teste de shapiro-wilk observa-se normalidade para CO2.

Teste de média

library(multcompView)

tukey = TukeyHSD(anova)
print(tukey)

  Tukey multiple comparisons of means
    95% family-wise confidence level

Fit: aov(formula = CO2 ~ Trat * Ciclo, data = database[-12, ])

$Trat
               diff        lwr        upr     p adj
SCT-SCEL  -49.87500  -91.64720  -8.102801 0.0134685
SR-SCEL  -100.16667 -142.62936 -57.703972 0.0000006
SS-SCEL   -33.36667  -75.82936   9.096028 0.1701357
SR-SCT    -50.29167  -92.75436  -7.828972 0.0144276
SS-SCT     16.50833  -25.95436  58.971028 0.7291949
SS-SR      66.80000   23.65786 109.942141 0.0008530

$Ciclo
          diff        lwr        upr     p adj
2-1 -124.96569 -167.42839  -82.50300 0.0000000
3-1 -213.27819 -255.74089 -170.81550 0.0000000
4-1 -181.98667 -225.12881 -138.84453 0.0000000
3-2  -88.31250 -130.08470  -46.54030 0.0000059
4-2  -57.02097  -99.48367  -14.55828 0.0044357
4-3   31.29153  -11.17117   73.75422 0.2163991

$`Trat:Ciclo`
                 diff        lwr           upr     p adj
SCT:1-SCEL:1   -50.50 -163.99047  6.299047e+01 0.9579824
SR:1-SCEL:1   -168.75 -282.24047 -5.525953e+01 0.0002447
SS:1-SCEL:1     38.00  -84.58371  1.605837e+02 0.9987110
SCEL:2-SCEL:1 -131.00 -244.49047 -1.750953e+01 0.0107465
SCT:2-SCEL:1  -178.75 -292.24047 -6.525953e+01 0.0000845
SR:2-SCEL:1   -226.25 -339.74047 -1.127595e+02 0.0000005
SS:2-SCEL:1   -164.00 -277.49047 -5.050953e+01 0.0004029
SCEL:3-SCEL:1 -224.00 -337.49047 -1.105095e+02 0.0000006
SCT:3-SCEL:1  -269.25 -382.74047 -1.557595e+02 0.0000000
SR:3-SCEL:1   -290.00 -403.49047 -1.765095e+02 0.0000000
SS:3-SCEL:1   -270.00 -383.49047 -1.565095e+02 0.0000000
SCEL:4-SCEL:1 -187.00 -300.49047 -7.350953e+01 0.0000348
SCT:4-SCEL:1  -243.00 -356.49047 -1.295095e+02 0.0000001
SR:4-SCEL:1   -265.00 -387.58371 -1.424163e+02 0.0000001
SS:4-SCEL:1   -227.75 -341.24047 -1.142595e+02 0.0000004
SR:1-SCT:1    -118.25 -231.74047 -4.759533e+00 0.0335706
SS:1-SCT:1      88.50  -34.08371  2.110837e+02 0.4141971
SCEL:2-SCT:1   -80.50 -193.99047  3.299047e+01 0.4436191
SCT:2-SCT:1   -128.25 -241.74047 -1.475953e+01 0.0138485
SR:2-SCT:1    -175.75 -289.24047 -6.225953e+01 0.0001165
SS:2-SCT:1    -113.50 -226.99047 -9.533356e-03 0.0499609
SCEL:3-SCT:1  -173.50 -286.99047 -6.000953e+01 0.0001480
SCT:3-SCT:1   -218.75 -332.24047 -1.052595e+02 0.0000011
SR:3-SCT:1    -239.50 -352.99047 -1.260095e+02 0.0000001
SS:3-SCT:1    -219.50 -332.99047 -1.060095e+02 0.0000010
SCEL:4-SCT:1  -136.50 -249.99047 -2.300953e+01 0.0063982
SCT:4-SCT:1   -192.50 -305.99047 -7.900953e+01 0.0000192
SR:4-SCT:1    -214.50 -337.08371 -9.191629e+01 0.0000099
SS:4-SCT:1    -177.25 -290.74047 -6.375953e+01 0.0000992
SS:1-SR:1      206.75   84.16629  3.293337e+02 0.0000216
SCEL:2-SR:1     37.75  -75.74047  1.512405e+02 0.9972405
SCT:2-SR:1     -10.00 -123.49047  1.034905e+02 1.0000000
SR:2-SR:1      -57.50 -170.99047  5.599047e+01 0.8905939
SS:2-SR:1        4.75 -108.74047  1.182405e+02 1.0000000
SCEL:3-SR:1    -55.25 -168.74047  5.824047e+01 0.9169425
SCT:3-SR:1    -100.50 -213.99047  1.299047e+01 0.1351888
SR:3-SR:1     -121.25 -234.74047 -7.759533e+00 0.0259070
SS:3-SR:1     -101.25 -214.74047  1.224047e+01 0.1281749
SCEL:4-SR:1    -18.25 -131.74047  9.524047e+01 0.9999997
SCT:4-SR:1     -74.25 -187.74047  3.924047e+01 0.5782882
SR:4-SR:1      -96.25 -218.83371  2.633371e+01 0.2821218
SS:4-SR:1      -59.00 -172.49047  5.449047e+01 0.8704931
SCEL:2-SS:1   -169.00 -291.58371 -4.641629e+01 0.0008795
SCT:2-SS:1    -216.75 -339.33371 -9.416629e+01 0.0000079
SR:2-SS:1     -264.25 -386.83371 -1.416663e+02 0.0000001
SS:2-SS:1     -202.00 -324.58371 -7.941629e+01 0.0000347
SCEL:3-SS:1   -262.00 -384.58371 -1.394163e+02 0.0000001
SCT:3-SS:1    -307.25 -429.83371 -1.846663e+02 0.0000000
SR:3-SS:1     -328.00 -450.58371 -2.054163e+02 0.0000000
SS:3-SS:1     -308.00 -430.58371 -1.854163e+02 0.0000000
SCEL:4-SS:1   -225.00 -347.58371 -1.024163e+02 0.0000034
SCT:4-SS:1    -281.00 -403.58371 -1.584163e+02 0.0000000
SR:4-SS:1     -303.00 -434.04750 -1.719525e+02 0.0000000
SS:4-SS:1     -265.75 -388.33371 -1.431663e+02 0.0000001
SCT:2-SCEL:2   -47.75 -161.24047  6.574047e+01 0.9736153
SR:2-SCEL:2    -95.25 -208.74047  1.824047e+01 0.1931633
SS:2-SCEL:2    -33.00 -146.49047  8.049047e+01 0.9993726
SCEL:3-SCEL:2  -93.00 -206.49047  2.049047e+01 0.2230510
SCT:3-SCEL:2  -138.25 -251.74047 -2.475953e+01 0.0054091
SR:3-SCEL:2   -159.00 -272.49047 -4.550953e+01 0.0006773
SS:3-SCEL:2   -139.00 -252.49047 -2.550953e+01 0.0050315
SCEL:4-SCEL:2  -56.00 -169.49047  5.749047e+01 0.9086677
SCT:4-SCEL:2  -112.00 -225.49047  1.490467e+00 0.0564488
SR:4-SCEL:2   -134.00 -256.58371 -1.141629e+01 0.0202182
SS:4-SCEL:2    -96.75 -210.24047  1.674047e+01 0.1749551
SR:2-SCT:2     -47.50 -160.99047  6.599047e+01 0.9747804
SS:2-SCT:2      14.75  -98.74047  1.282405e+02 1.0000000
SCEL:3-SCT:2   -45.25 -158.74047  6.824047e+01 0.9835885
SCT:3-SCT:2    -90.50 -203.99047  2.299047e+01 0.2599416
SR:3-SCT:2    -111.25 -224.74047  2.240467e+00 0.0599629
SS:3-SCT:2     -91.25 -204.74047  2.224047e+01 0.2484667
SCEL:4-SCT:2    -8.25 -121.74047  1.052405e+02 1.0000000
SCT:4-SCT:2    -64.25 -177.74047  4.924047e+01 0.7851133
SR:4-SCT:2     -86.25 -208.83371  3.633371e+01 0.4571554
SS:4-SCT:2     -49.00 -162.49047  6.449047e+01 0.9671716
SS:2-SR:2       62.25  -51.24047  1.757405e+02 0.8202359
SCEL:3-SR:2      2.25 -111.24047  1.157405e+02 1.0000000
SCT:3-SR:2     -43.00 -156.49047  7.049047e+01 0.9897871
SR:3-SR:2      -63.75 -177.24047  4.974047e+01 0.7941687
SS:3-SR:2      -43.75 -157.24047  6.974047e+01 0.9879748
SCEL:4-SR:2     39.25  -74.24047  1.527405e+02 0.9958606
SCT:4-SR:2     -16.75 -130.24047  9.674047e+01 0.9999999
SR:4-SR:2      -38.75 -161.33371  8.383371e+01 0.9984026
SS:4-SR:2       -1.50 -114.99047  1.119905e+02 1.0000000
SCEL:3-SS:2    -60.00 -173.49047  5.349047e+01 0.8559849
SCT:3-SS:2    -105.25 -218.74047  8.240467e+00 0.0956009
SR:3-SS:2     -126.00 -239.49047 -1.250953e+01 0.0169900
SS:3-SS:2     -106.00 -219.49047  7.490467e+00 0.0903387
SCEL:4-SS:2    -23.00 -136.49047  9.049047e+01 0.9999928
SCT:4-SS:2     -79.00 -192.49047  3.449047e+01 0.4751593
SR:4-SS:2     -101.00 -223.58371  2.158371e+01 0.2160321
SS:4-SS:2      -63.75 -177.24047  4.974047e+01 0.7941687
SCT:3-SCEL:3   -45.25 -158.74047  6.824047e+01 0.9835885
SR:3-SCEL:3    -66.00 -179.49047  4.749047e+01 0.7521062
SS:3-SCEL:3    -46.00 -159.49047  6.749047e+01 0.9809714
SCEL:4-SCEL:3   37.00  -76.49047  1.504905e+02 0.9977704
SCT:4-SCEL:3   -19.00 -132.49047  9.449047e+01 0.9999994
SR:4-SCEL:3    -41.00 -163.58371  8.158371e+01 0.9970756
SS:4-SCEL:3     -3.75 -117.24047  1.097405e+02 1.0000000
SR:3-SCT:3     -20.75 -134.24047  9.274047e+01 0.9999982
SS:3-SCT:3      -0.75 -114.24047  1.127405e+02 1.0000000
SCEL:4-SCT:3    82.25  -31.24047  1.957405e+02 0.4078529
SCT:4-SCT:3     26.25  -87.24047  1.397405e+02 0.9999604
SR:4-SCT:3       4.25 -118.33371  1.268337e+02 1.0000000
SS:4-SCT:3      41.50  -71.99047  1.549905e+02 0.9927553
SS:3-SR:3       20.00  -93.49047  1.334905e+02 0.9999989
SCEL:4-SR:3    103.00  -10.49047  2.164905e+02 0.1129521
SCT:4-SR:3      47.00  -66.49047  1.604905e+02 0.9769933
SR:4-SR:3       25.00  -97.58371  1.475837e+02 0.9999922
SS:4-SR:3       62.25  -51.24047  1.757405e+02 0.8202359
SCEL:4-SS:3     83.00  -30.49047  1.964905e+02 0.3929202
SCT:4-SS:3      27.00  -86.49047  1.404905e+02 0.9999436
SR:4-SS:3        5.00 -117.58371  1.275837e+02 1.0000000
SS:4-SS:3       42.25  -71.24047  1.557405e+02 0.9913738
SCT:4-SCEL:4   -56.00 -169.49047  5.749047e+01 0.9086677
SR:4-SCEL:4    -78.00 -200.58371  4.458371e+01 0.6228106
SS:4-SCEL:4    -40.75 -154.24047  7.274047e+01 0.9939512
SR:4-SCT:4     -22.00 -144.58371  1.005837e+02 0.9999986
SS:4-SCT:4      15.25  -98.24047  1.287405e+02 1.0000000
SS:4-SR:4       37.25  -85.33371  1.598337e+02 0.9989671

tukey.cld = multcompLetters4(anova, tukey)
print(tukey.cld)

$Trat
SCEL   SS  SCT   SR 
 "a" "ab"  "b"  "c" 

$Ciclo
  1   2   4   3 
"a" "b" "c" "c" 

$`Trat:Ciclo`
  SS:1 SCEL:1  SCT:1 SCEL:2   SS:2   SR:1  SCT:2 SCEL:4 SCEL:3   SR:2   SS:4 
   "a"    "a"   "ab"   "bc"   "cd"   "cd"  "cde"  "cde"  "cde"  "cde"  "cde" 
 SCT:4   SR:4  SCT:3   SS:3   SR:3 
 "cde"   "de"   "de"   "de"    "e" 

library(dplyr)
data_summary = group_by(database, Trat, Ciclo) %>%
  summarise(mean=mean(CO2), sd=sd(CO2)) %>%
  arrange(desc(mean))

`summarise()` has grouped output by 'Trat'. You can override using the `.groups` argument.

print(data_summary)

cld = as.data.frame.list(tukey.cld$`Trat:Ciclo`)
data_summary$Tukey = cld$Letters
print(data_summary)

O pacote MulticompView fornece as letras a partir dos valores de P obtidos com o teste de Tukey, observe que ele oferece primeiro para o primeiro fator (Trat), depois para o segundo fator (Ciclo) e por ultimo para a interação, que é o que te interessa, a menos que tivesse sido significativo para interação. O pacote dplyr te fornece a média e SD para todos os tratamentos, e na sequencia eu adicionei outra coluna neste mesma tabela, com as letras obtidas pelo pacote MulticompView, como o dplyr fornece as medias de modo decrescente então as letras já estão na ordem correta.

Plot

library(ggplot2)

plot1=ggplot(data_summary, aes(x = factor(Trat), y = mean, fill = Ciclo, colour = Ciclo)) + 
  geom_bar(stat = "identity", position = "dodge", alpha = 0.5)  +
  geom_errorbar(aes(ymin=mean-sd, ymax=mean+sd), position = position_dodge(0.9), width = 0.25) +
  labs(x="Tratamentos", y="CO2") +
  theme_bw() + 
  theme(panel.grid.major = element_blank(), panel.grid.minor = element_blank(),legend.position = c(0.2, 0.9),  legend.direction = "horizontal")+
  geom_text(aes(label=Tukey), position = position_dodge(0.90), size = 3, 
            vjust=-0.8, hjust=-0.5, colour = "Black")+ylim(0, 500)
plot1

Caso vc não queira apresentar em tabela, este plot pode ser uma alternativa

---

2 - N2O

Outliers

boxplot(database$N2O)

O boxplot mostra que não tem outliers.

Análise de variancia

anova1 = aov(N2O~Trat*Ciclo, data = database) 
summary(anova1)

            Df    Sum Sq   Mean Sq F value Pr(>F)  
Trat         3 0.0000538 1.794e-05   0.381 0.7669  
Ciclo        3 0.0004187 1.396e-04   2.967 0.0414 *
Trat:Ciclo   9 0.0002440 2.711e-05   0.576 0.8096  
Residuals   47 0.0022112 4.705e-05                 
---
Signif. codes:  0 ‘***’ 0.001 ‘**’ 0.01 ‘*’ 0.05 ‘.’ 0.1 ‘ ’ 1

Observe que aqui eu não retirei a linha 12, visto que para N2O não foi considerado outlier. Só deu diferença para ciclos, mas primeiro veremos a normalidade.

Análise de pressuposição de normalidade

hist(rstandard(anova1))

shapiro.test(rstandard(anova1))

    Shapiro-Wilk normality test

data:  rstandard(anova1)
W = 0.9852, p-value = 0.6504

Por incrivel que pareça deu normal e o histograma ficou bonito, achei que não daria normalidade devido aqueles resultados obtidos com o ExpDes, mas a normalidade é testada no residuo então as vezes os dados brutos pode nos passar uma visão enganosa.

Teste de média

tukey1 = TukeyHSD(anova1)
print(tukey1)

  Tukey multiple comparisons of means
    95% family-wise confidence level

Fit: aov(formula = N2O ~ Trat * Ciclo, data = database)

$Trat
                 diff          lwr         upr     p adj
SCT-SCEL -0.000493125 -0.006951912 0.005965662 0.9969820
SR-SCEL  -0.000916625 -0.007482176 0.005648926 0.9822408
SS-SCEL  -0.002450625 -0.008909412 0.004008162 0.7440746
SR-SCT   -0.000423500 -0.006989051 0.006142051 0.9981715
SS-SCT   -0.001957500 -0.008416287 0.004501287 0.8507207
SS-SR    -0.001534000 -0.008099551 0.005031551 0.9244274

$Ciclo
             diff           lwr         upr     p adj
2-1  0.0047287500 -0.0017300367 0.011187537 0.2216622
3-1  0.0060100000 -0.0004487867 0.012468787 0.0765726
4-1  0.0006540646 -0.0059114861 0.007219615 0.9933727
3-2  0.0012812500 -0.0051775367 0.007740037 0.9517796
4-2 -0.0040746854 -0.0106402361 0.002490865 0.3597442
4-3 -0.0053559354 -0.0119214861 0.001209615 0.1458654

$`Trat:Ciclo`
                    diff          lwr         upr     p adj
SCT:1-SCEL:1  -0.0008225 -0.018363785 0.016718785 1.0000000
SR:1-SCEL:1   -0.0008750 -0.018416285 0.016666285 1.0000000
SS:1-SCEL:1   -0.0046025 -0.022143785 0.012938785 0.9998171
SCEL:2-SCEL:1  0.0084225 -0.009118785 0.025963785 0.9256531
SCT:2-SCEL:1   0.0014225 -0.016118785 0.018963785 1.0000000
SR:2-SCEL:1   -0.0001525 -0.017693785 0.017388785 1.0000000
SS:2-SCEL:1    0.0029225 -0.014618785 0.020463785 0.9999995
SCEL:3-SCEL:1  0.0030975 -0.014443785 0.020638785 0.9999989
SCT:3-SCEL:1   0.0057975 -0.011743785 0.023338785 0.9974748
SR:3-SCEL:1    0.0046725 -0.012868785 0.022213785 0.9997808
SS:3-SCEL:1    0.0041725 -0.013368785 0.021713785 0.9999452
SCEL:4-SCEL:1 -0.0024275 -0.019968785 0.015113785 1.0000000
SCT:4-SCEL:1   0.0007225 -0.016818785 0.018263785 1.0000000
SR:4-SCEL:1    0.0019225 -0.017024253 0.020869253 1.0000000
SS:4-SCEL:1   -0.0032025 -0.020743785 0.014338785 0.9999983
SR:1-SCT:1    -0.0000525 -0.017593785 0.017488785 1.0000000
SS:1-SCT:1    -0.0037800 -0.021321285 0.013761285 0.9999844
SCEL:2-SCT:1   0.0092450 -0.008296285 0.026786285 0.8600339
SCT:2-SCT:1    0.0022450 -0.015296285 0.019786285 1.0000000
SR:2-SCT:1     0.0006700 -0.016871285 0.018211285 1.0000000
SS:2-SCT:1     0.0037450 -0.013796285 0.021286285 0.9999862
SCEL:3-SCT:1   0.0039200 -0.013621285 0.021461285 0.9999751
SCT:3-SCT:1    0.0066200 -0.010921285 0.024161285 0.9903386
SR:3-SCT:1     0.0054950 -0.012046285 0.023036285 0.9985851
SS:3-SCT:1     0.0049950 -0.012546285 0.022536285 0.9995186
SCEL:4-SCT:1  -0.0016050 -0.019146285 0.015936285 1.0000000
SCT:4-SCT:1    0.0015450 -0.015996285 0.019086285 1.0000000
SR:4-SCT:1     0.0027450 -0.016201753 0.021691753 0.9999999
SS:4-SCT:1    -0.0023800 -0.019921285 0.015161285 1.0000000
SS:1-SR:1     -0.0037275 -0.021268785 0.013813785 0.9999870
SCEL:2-SR:1    0.0092975 -0.008243785 0.026838785 0.8549880
SCT:2-SR:1     0.0022975 -0.015243785 0.019838785 1.0000000
SR:2-SR:1      0.0007225 -0.016818785 0.018263785 1.0000000
SS:2-SR:1      0.0037975 -0.013743785 0.021338785 0.9999835
SCEL:3-SR:1    0.0039725 -0.013568785 0.021513785 0.9999706
SCT:3-SR:1     0.0066725 -0.010868785 0.024213785 0.9895819
SR:3-SR:1      0.0055475 -0.011993785 0.023088785 0.9984297
SS:3-SR:1      0.0050475 -0.012493785 0.022588785 0.9994568
SCEL:4-SR:1   -0.0015525 -0.019093785 0.015988785 1.0000000
SCT:4-SR:1     0.0015975 -0.015943785 0.019138785 1.0000000
SR:4-SR:1      0.0027975 -0.016149253 0.021744253 0.9999999
SS:4-SR:1     -0.0023275 -0.019868785 0.015213785 1.0000000
SCEL:2-SS:1    0.0130250 -0.004516285 0.030566285 0.3695376
SCT:2-SS:1     0.0060250 -0.011516285 0.023566285 0.9962202
SR:2-SS:1      0.0044500 -0.013091285 0.021991285 0.9998785
SS:2-SS:1      0.0075250 -0.010016285 0.025066285 0.9693405
SCEL:3-SS:1    0.0077000 -0.009841285 0.025241285 0.9628872
SCT:3-SS:1     0.0104000 -0.007141285 0.027941285 0.7283768
SR:3-SS:1      0.0092750 -0.008266285 0.026816285 0.8571628
SS:3-SS:1      0.0087750 -0.008766285 0.026316285 0.9006533
SCEL:4-SS:1    0.0021750 -0.015366285 0.019716285 1.0000000
SCT:4-SS:1     0.0053250 -0.012216285 0.022866285 0.9990017
SR:4-SS:1      0.0065250 -0.012421753 0.025471753 0.9961154
SS:4-SS:1      0.0014000 -0.016141285 0.018941285 1.0000000
SCT:2-SCEL:2  -0.0070000 -0.024541285 0.010541285 0.9837291
SR:2-SCEL:2   -0.0085750 -0.026116285 0.008966285 0.9154112
SS:2-SCEL:2   -0.0055000 -0.023041285 0.012041285 0.9985709
SCEL:3-SCEL:2 -0.0053250 -0.022866285 0.012216285 0.9990017
SCT:3-SCEL:2  -0.0026250 -0.020166285 0.014916285 0.9999999
SR:3-SCEL:2   -0.0037500 -0.021291285 0.013791285 0.9999860
SS:3-SCEL:2   -0.0042500 -0.021791285 0.013291285 0.9999311
SCEL:4-SCEL:2 -0.0108500 -0.028391285 0.006691285 0.6680222
SCT:4-SCEL:2  -0.0077000 -0.025241285 0.009841285 0.9628872
SR:4-SCEL:2   -0.0065000 -0.025446753 0.012446753 0.9962664
SS:4-SCEL:2   -0.0116250 -0.029166285 0.005916285 0.5589241
SR:2-SCT:2    -0.0015750 -0.019116285 0.015966285 1.0000000
SS:2-SCT:2     0.0015000 -0.016041285 0.019041285 1.0000000
SCEL:3-SCT:2   0.0016750 -0.015866285 0.019216285 1.0000000
SCT:3-SCT:2    0.0043750 -0.013166285 0.021916285 0.9999014
SR:3-SCT:2     0.0032500 -0.014291285 0.020791285 0.9999979
SS:3-SCT:2     0.0027500 -0.014791285 0.020291285 0.9999998
SCEL:4-SCT:2  -0.0038500 -0.021391285 0.013691285 0.9999803
SCT:4-SCT:2   -0.0007000 -0.018241285 0.016841285 1.0000000
SR:4-SCT:2     0.0005000 -0.018446753 0.019446753 1.0000000
SS:4-SCT:2    -0.0046250 -0.022166285 0.012916285 0.9998061
SS:2-SR:2      0.0030750 -0.014466285 0.020616285 0.9999990
SCEL:3-SR:2    0.0032500 -0.014291285 0.020791285 0.9999979
SCT:3-SR:2     0.0059500 -0.011591285 0.023491285 0.9966812
SR:3-SR:2      0.0048250 -0.012716285 0.022366285 0.9996789
SS:3-SR:2      0.0043250 -0.013216285 0.021866285 0.9999144
SCEL:4-SR:2   -0.0022750 -0.019816285 0.015266285 1.0000000
SCT:4-SR:2     0.0008750 -0.016666285 0.018416285 1.0000000
SR:4-SR:2      0.0020750 -0.016871753 0.021021753 1.0000000
SS:4-SR:2     -0.0030500 -0.020591285 0.014491285 0.9999991
SCEL:3-SS:2    0.0001750 -0.017366285 0.017716285 1.0000000
SCT:3-SS:2     0.0028750 -0.014666285 0.020416285 0.9999996
SR:3-SS:2      0.0017500 -0.015791285 0.019291285 1.0000000
SS:3-SS:2      0.0012500 -0.016291285 0.018791285 1.0000000
SCEL:4-SS:2   -0.0053500 -0.022891285 0.012191285 0.9989480
SCT:4-SS:2    -0.0022000 -0.019741285 0.015341285 1.0000000
SR:4-SS:2     -0.0010000 -0.019946753 0.017946753 1.0000000
SS:4-SS:2     -0.0061250 -0.023666285 0.011416285 0.9955238
SCT:3-SCEL:3   0.0027000 -0.014841285 0.020241285 0.9999998
SR:3-SCEL:3    0.0015750 -0.015966285 0.019116285 1.0000000
SS:3-SCEL:3    0.0010750 -0.016466285 0.018616285 1.0000000
SCEL:4-SCEL:3 -0.0055250 -0.023066285 0.012016285 0.9984980
SCT:4-SCEL:3  -0.0023750 -0.019916285 0.015166285 1.0000000
SR:4-SCEL:3   -0.0011750 -0.020121753 0.017771753 1.0000000
SS:4-SCEL:3   -0.0063000 -0.023841285 0.011241285 0.9940506
SR:3-SCT:3    -0.0011250 -0.018666285 0.016416285 1.0000000
SS:3-SCT:3    -0.0016250 -0.019166285 0.015916285 1.0000000
SCEL:4-SCT:3  -0.0082250 -0.025766285 0.009316285 0.9376409
SCT:4-SCT:3   -0.0050750 -0.022616285 0.012466285 0.9994217
SR:4-SCT:3    -0.0038750 -0.022821753 0.015071753 0.9999921
SS:4-SCT:3    -0.0090000 -0.026541285 0.008541285 0.8822411
SS:3-SR:3     -0.0005000 -0.018041285 0.017041285 1.0000000
SCEL:4-SR:3   -0.0071000 -0.024641285 0.010441285 0.9815059
SCT:4-SR:3    -0.0039500 -0.021491285 0.013591285 0.9999726
SR:4-SR:3     -0.0027500 -0.021696753 0.016196753 0.9999999
SS:4-SR:3     -0.0078750 -0.025416285 0.009666285 0.9554915
SCEL:4-SS:3   -0.0066000 -0.024141285 0.010941285 0.9906150
SCT:4-SS:3    -0.0034500 -0.020991285 0.014091285 0.9999953
SR:4-SS:3     -0.0022500 -0.021196753 0.016696753 1.0000000
SS:4-SS:3     -0.0073750 -0.024916285 0.010166285 0.9741719
SCT:4-SCEL:4   0.0031500 -0.014391285 0.020691285 0.9999986
SR:4-SCEL:4    0.0043500 -0.014596753 0.023296753 0.9999649
SS:4-SCEL:4   -0.0007750 -0.018316285 0.016766285 1.0000000
SR:4-SCT:4     0.0012000 -0.017746753 0.020146753 1.0000000
SS:4-SCT:4    -0.0039250 -0.021466285 0.013616285 0.9999747
SS:4-SR:4     -0.0051250 -0.024071753 0.013821753 0.9997367

tukey.cld1 = multcompLetters4(anova1, tukey1)
print(tukey.cld1)

$Trat
$Trat$Letters
SCEL  SCT   SR   SS 
 "a"  "a"  "a"  "a" 

$Trat$LetterMatrix
        a
SCEL TRUE
SCT  TRUE
SR   TRUE
SS   TRUE


$Ciclo
$Ciclo$Letters
  3   2   4   1 
"a" "a" "a" "a" 

$Ciclo$LetterMatrix
     a
3 TRUE
2 TRUE
4 TRUE
1 TRUE


$`Trat:Ciclo`
$`Trat:Ciclo`$Letters
SCEL:2  SCT:3   SR:3   SS:3 SCEL:3   SS:2   SR:4  SCT:2  SCT:4 SCEL:1   SR:2 
   "a"    "a"    "a"    "a"    "a"    "a"    "a"    "a"    "a"    "a"    "a" 
 SCT:1   SR:1 SCEL:4   SS:4   SS:1 
   "a"    "a"    "a"    "a"    "a" 

$`Trat:Ciclo`$LetterMatrix
          a
SCEL:2 TRUE
SCT:3  TRUE
SR:3   TRUE
SS:3   TRUE
SCEL:3 TRUE
SS:2   TRUE
SR:4   TRUE
SCT:2  TRUE
SCT:4  TRUE
SCEL:1 TRUE
SR:2   TRUE
SCT:1  TRUE
SR:1   TRUE
SCEL:4 TRUE
SS:4   TRUE
SS:1   TRUE

data_summary1 = group_by(database, Trat, Ciclo) %>%
  summarise(mean=mean(N2O), sd=sd(N2O)) %>%
  arrange(desc(mean))

`summarise()` has grouped output by 'Trat'. You can override using the `.groups` argument.

print(data_summary1)

cld1 = as.data.frame.list(tukey.cld1$`Trat:Ciclo`)
data_summary1$Tukey = cld1$Letters
print(data_summary1)

Novamente essa merda deu significativa na analise de variancia, mas sem resultados significativos quando aplicado o teste de tukey, imagino que a análise de variancia esteja a 0.05 enquanto que o teste de tukey esteja a 0.01 de significancia, segunda-feira eu confirmo com o Simón isso, pq ele já passou por isso e deve ter arrumado uma solução.

Plot

plot2=ggplot(data_summary1, aes(x = factor(Trat), y = mean, fill = Ciclo, colour = Ciclo)) + 
  geom_bar(stat = "identity", position = "dodge", alpha = 0.5) +
  geom_errorbar(aes(ymin=mean-sd, ymax=mean+sd), position = position_dodge(0.9), width = 0.25) +
  labs(x="Tratamentos", y="N2O")+ theme_bw() + 
  theme(panel.grid.major = element_blank(), panel.grid.minor = element_blank(),legend.position = c(0.5, 0.9),  legend.direction = "horizontal")+
  geom_text(aes(label=Tukey), position = position_dodge(0.90), size = 3, 
            vjust=-0.8, hjust=-0.5, colour = "Black")
plot2

Há não tem como dar significativo, agr que percebi que o SD é maior do que a propria media em alguns casos.

---

3 - CH4

Outliers

boxplot(database$CH4)

outliers3 = boxplot(database$CH4)$out 

outliers3

[1] -0.07253 -0.02992 -0.02868 -0.05667  0.04340 -0.18370 -0.03580 -0.03580

database[which(database$CH4 %in% outliers3),] 

Caramba, muitos outliers. Vou retirar, mas alguns tratamentos perderão duas de quatro repetições, dai depois vc escolhe se mantem ou retira.

Análise de variancia

anova3 = aov(CH4~Trat*Ciclo, data = database[-c(1,2,7,16,19,28,39,55),]) 
summary(anova3)

            Df    Sum Sq   Mean Sq F value Pr(>F)
Trat         3 0.0001811 6.038e-05   1.845  0.155
Ciclo        3 0.0000630 2.099e-05   0.641  0.593
Trat:Ciclo   9 0.0002586 2.874e-05   0.878  0.553
Residuals   39 0.0012763 3.273e-05               

Testei com e sem outliers, em ambas as formas não foi significativo.

Análise de pressuposição de normalidade

hist(rstandard(anova3))

shapiro.test(rstandard(anova3))

    Shapiro-Wilk normality test

data:  rstandard(anova3)
W = 0.97864, p-value = 0.432

Tambem testei com e sem outliers, com outliers os dados não são normais, enquanto que quando retirado os outliers (na forma em que deixei), existe normalidade de residuo.

Teste de média

tukey3 = TukeyHSD(anova3)
print(tukey3)

  Tukey multiple comparisons of means
    95% family-wise confidence level

Fit: aov(formula = CH4 ~ Trat * Ciclo, data = database[-c(1, 2, 7, 16, 19, 28, 39, 55), ])

$Trat
                 diff           lwr         upr     p adj
SCT-SCEL -0.001731538 -0.0077525868 0.004289510 0.8667240
SR-SCEL  -0.003514890 -0.0094274422 0.002397662 0.3931101
SS-SCEL   0.001200872 -0.0046160135 0.007017757 0.9449126
SR-SCT   -0.001783352 -0.0076959037 0.004129200 0.8496485
SS-SCT    0.002932410 -0.0028844750 0.008749296 0.5358604
SS-SR     0.004715762 -0.0009887454 0.010420269 0.1361522

$Ciclo
             diff          lwr         upr     p adj
2-1 -0.0020129816 -0.008051923 0.004025960 0.8077375
3-1 -0.0029307065 -0.008876015 0.003014602 0.5543677
4-1 -0.0023547119 -0.008393653 0.003684230 0.7235323
3-2 -0.0009177249 -0.006622232 0.004786782 0.9726669
4-2 -0.0003417302 -0.006143758 0.005460297 0.9985695
4-3  0.0005759946 -0.005128513 0.006280502 0.9929314

$`Trat:Ciclo`
                       diff          lwr         upr     p adj
SCT:1-SCEL:1   1.658333e-03 -0.017437053 0.020753719 1.0000000
SR:1-SCEL:1   -6.570000e-03 -0.023649432 0.010509432 0.9863944
SS:1-SCEL:1   -3.541667e-04 -0.016330513 0.015622179 1.0000000
SCEL:2-SCEL:1 -4.676667e-03 -0.020653013 0.011299679 0.9991763
SCT:2-SCEL:1  -5.560000e-03 -0.022639432 0.011519432 0.9973806
SR:2-SCEL:1   -6.776667e-03 -0.022753013 0.009199679 0.9680390
SS:2-SCEL:1    2.873333e-03 -0.014206099 0.019952766 0.9999992
SCEL:3-SCEL:1 -1.626667e-03 -0.018706099 0.015452766 1.0000000
SCT:3-SCEL:1  -5.126667e-03 -0.021103013 0.010849679 0.9977500
SR:3-SCEL:1   -8.626667e-03 -0.024603013 0.007349679 0.8242869
SS:3-SCEL:1   -2.751667e-03 -0.018728013 0.013224679 0.9999989
SCEL:4-SCEL:1 -3.526667e-03 -0.020606099 0.013552766 0.9999883
SCT:4-SCEL:1  -5.701667e-03 -0.021678013 0.010274679 0.9933272
SR:4-SCEL:1   -1.560000e-03 -0.018639432 0.015519432 1.0000000
SS:4-SCEL:1   -4.401667e-03 -0.020378013 0.011574679 0.9995879
SR:1-SCT:1    -8.228333e-03 -0.027323719 0.010867053 0.9636256
SS:1-SCT:1    -2.012500e-03 -0.020127974 0.016102974 1.0000000
SCEL:2-SCT:1  -6.335000e-03 -0.024450474 0.011780474 0.9945429
SCT:2-SCT:1   -7.218333e-03 -0.026313719 0.011877053 0.9884249
SR:2-SCT:1    -8.435000e-03 -0.026550474 0.009680474 0.9336980
SS:2-SCT:1     1.215000e-03 -0.017880386 0.020310386 1.0000000
SCEL:3-SCT:1  -3.285000e-03 -0.022380386 0.015810386 0.9999990
SCT:3-SCT:1   -6.785000e-03 -0.024900474 0.011330474 0.9893840
SR:3-SCT:1    -1.028500e-02 -0.028400474 0.007830474 0.7683169
SS:3-SCT:1    -4.410000e-03 -0.022525474 0.013705474 0.9999061
SCEL:4-SCT:1  -5.185000e-03 -0.024280386 0.013910386 0.9996522
SCT:4-SCT:1   -7.360000e-03 -0.025475474 0.010755474 0.9778268
SR:4-SCT:1    -3.218333e-03 -0.022313719 0.015877053 0.9999992
SS:4-SCT:1    -6.060000e-03 -0.024175474 0.012055474 0.9965217
SS:1-SR:1      6.215833e-03 -0.009760513 0.022192179 0.9849086
SCEL:2-SR:1    1.893333e-03 -0.014083013 0.017869679 1.0000000
SCT:2-SR:1     1.010000e-03 -0.016069432 0.018089432 1.0000000
SR:2-SR:1     -2.066667e-04 -0.016183013 0.015769679 1.0000000
SS:2-SR:1      9.443333e-03 -0.007636099 0.026522766 0.7990969
SCEL:3-SR:1    4.943333e-03 -0.012136099 0.022022766 0.9992750
SCT:3-SR:1     1.443333e-03 -0.014533013 0.017419679 1.0000000
SR:3-SR:1     -2.056667e-03 -0.018033013 0.013919679 1.0000000
SS:3-SR:1      3.818333e-03 -0.012158013 0.019794679 0.9999251
SCEL:4-SR:1    3.043333e-03 -0.014036099 0.020122766 0.9999983
SCT:4-SR:1     8.683333e-04 -0.015108013 0.016844679 1.0000000
SR:4-SR:1      5.010000e-03 -0.012069432 0.022089432 0.9991568
SS:4-SR:1      2.168333e-03 -0.013808013 0.018144679 1.0000000
SCEL:2-SS:1   -4.322500e-03 -0.019113722 0.010468722 0.9991917
SCT:2-SS:1    -5.205833e-03 -0.021182179 0.010770513 0.9973544
SR:2-SS:1     -6.422500e-03 -0.021213722 0.008368722 0.9613064
SS:2-SS:1      3.227500e-03 -0.012748846 0.019203846 0.9999912
SCEL:3-SS:1   -1.272500e-03 -0.017248846 0.014703846 1.0000000
SCT:3-SS:1    -4.772500e-03 -0.019563722 0.010018722 0.9976151
SR:3-SS:1     -8.272500e-03 -0.023063722 0.006518722 0.7861039
SS:3-SS:1     -2.397500e-03 -0.017188722 0.012393722 0.9999995
SCEL:4-SS:1   -3.172500e-03 -0.019148846 0.012803846 0.9999930
SCT:4-SS:1    -5.347500e-03 -0.020138722 0.009443722 0.9924285
SR:4-SS:1     -1.205833e-03 -0.017182179 0.014770513 1.0000000
SS:4-SS:1     -4.047500e-03 -0.018838722 0.010743722 0.9996193
SCT:2-SCEL:2  -8.833333e-04 -0.016859679 0.015093013 1.0000000
SR:2-SCEL:2   -2.100000e-03 -0.016891222 0.012691222 0.9999999
SS:2-SCEL:2    7.550000e-03 -0.008426346 0.023526346 0.9261453
SCEL:3-SCEL:2  3.050000e-03 -0.012926346 0.019026346 0.9999958
SCT:3-SCEL:2  -4.500000e-04 -0.015241222 0.014341222 1.0000000
SR:3-SCEL:2   -3.950000e-03 -0.018741222 0.010841222 0.9997139
SS:3-SCEL:2    1.925000e-03 -0.012866222 0.016716222 1.0000000
SCEL:4-SCEL:2  1.150000e-03 -0.014826346 0.017126346 1.0000000
SCT:4-SCEL:2  -1.025000e-03 -0.015816222 0.013766222 1.0000000
SR:4-SCEL:2    3.116667e-03 -0.012859679 0.019093013 0.9999944
SS:4-SCEL:2    2.750000e-04 -0.014516222 0.015066222 1.0000000
SR:2-SCT:2    -1.216667e-03 -0.017193013 0.014759679 1.0000000
SS:2-SCT:2     8.433333e-03 -0.008646099 0.025512766 0.8996922
SCEL:3-SCT:2   3.933333e-03 -0.013146099 0.021012766 0.9999528
SCT:3-SCT:2    4.333333e-04 -0.015543013 0.016409679 1.0000000
SR:3-SCT:2    -3.066667e-03 -0.019043013 0.012909679 0.9999955
SS:3-SCT:2     2.808333e-03 -0.013168013 0.018784679 0.9999986
SCEL:4-SCT:2   2.033333e-03 -0.015046099 0.019112766 1.0000000
SCT:4-SCT:2   -1.416667e-04 -0.016118013 0.015834679 1.0000000
SR:4-SCT:2     4.000000e-03 -0.013079432 0.021079432 0.9999418
SS:4-SCT:2     1.158333e-03 -0.014818013 0.017134679 1.0000000
SS:2-SR:2      9.650000e-03 -0.006326346 0.025626346 0.6862181
SCEL:3-SR:2    5.150000e-03 -0.010826346 0.021126346 0.9976389
SCT:3-SR:2     1.650000e-03 -0.013141222 0.016441222 1.0000000
SR:3-SR:2     -1.850000e-03 -0.016641222 0.012941222 1.0000000
SS:3-SR:2      4.025000e-03 -0.010766222 0.018816222 0.9996433
SCEL:4-SR:2    3.250000e-03 -0.012726346 0.019226346 0.9999903
SCT:4-SR:2     1.075000e-03 -0.013716222 0.015866222 1.0000000
SR:4-SR:2      5.216667e-03 -0.010759679 0.021193013 0.9972960
SS:4-SR:2      2.375000e-03 -0.012416222 0.017166222 0.9999996
SCEL:3-SS:2   -4.500000e-03 -0.021579432 0.012579432 0.9997561
SCT:3-SS:2    -8.000000e-03 -0.023976346 0.007976346 0.8898590
SR:3-SS:2     -1.150000e-02 -0.027476346 0.004476346 0.4070702
SS:3-SS:2     -5.625000e-03 -0.021601346 0.010351346 0.9941616
SCEL:4-SS:2   -6.400000e-03 -0.023479432 0.010679432 0.9893365
SCT:4-SS:2    -8.575000e-03 -0.024551346 0.007401346 0.8303221
SR:4-SS:2     -4.433333e-03 -0.021512766 0.012646099 0.9997958
SS:4-SS:2     -7.275000e-03 -0.023251346 0.008701346 0.9438688
SCT:3-SCEL:3  -3.500000e-03 -0.019476346 0.012476346 0.9999749
SR:3-SCEL:3   -7.000000e-03 -0.022976346 0.008976346 0.9584039
SS:3-SCEL:3   -1.125000e-03 -0.017101346 0.014851346 1.0000000
SCEL:4-SCEL:3 -1.900000e-03 -0.018979432 0.015179432 1.0000000
SCT:4-SCEL:3  -4.075000e-03 -0.020051346 0.011901346 0.9998344
SR:4-SCEL:3    6.666667e-05 -0.017012766 0.017146099 1.0000000
SS:4-SCEL:3   -2.775000e-03 -0.018751346 0.013201346 0.9999988
SR:3-SCT:3    -3.500000e-03 -0.018291222 0.011291222 0.9999338
SS:3-SCT:3     2.375000e-03 -0.012416222 0.017166222 0.9999996
SCEL:4-SCT:3   1.600000e-03 -0.014376346 0.017576346 1.0000000
SCT:4-SCT:3   -5.750000e-04 -0.015366222 0.014216222 1.0000000
SR:4-SCT:3     3.566667e-03 -0.012409679 0.019543013 0.9999681
SS:4-SCT:3     7.250000e-04 -0.014066222 0.015516222 1.0000000
SS:3-SR:3      5.875000e-03 -0.008916222 0.020666222 0.9818258
SCEL:4-SR:3    5.100000e-03 -0.010876346 0.021076346 0.9978714
SCT:4-SR:3     2.925000e-03 -0.011866222 0.017716222 0.9999933
SR:4-SR:3      7.066667e-03 -0.008909679 0.023043013 0.9551603
SS:4-SR:3      4.225000e-03 -0.010566222 0.019016222 0.9993757
SCEL:4-SS:3   -7.750000e-04 -0.016751346 0.015201346 1.0000000
SCT:4-SS:3    -2.950000e-03 -0.017741222 0.011841222 0.9999925
SR:4-SS:3      1.191667e-03 -0.014784679 0.017168013 1.0000000
SS:4-SS:3     -1.650000e-03 -0.016441222 0.013141222 1.0000000
SCT:4-SCEL:4  -2.175000e-03 -0.018151346 0.013801346 1.0000000
SR:4-SCEL:4    1.966667e-03 -0.015112766 0.019046099 1.0000000
SS:4-SCEL:4   -8.750000e-04 -0.016851346 0.015101346 1.0000000
SR:4-SCT:4     4.141667e-03 -0.011834679 0.020118013 0.9997989
SS:4-SCT:4     1.300000e-03 -0.013491222 0.016091222 1.0000000
SS:4-SR:4     -2.841667e-03 -0.018818013 0.013134679 0.9999984

tukey.cld3 = multcompLetters4(anova3, tukey3)
print(tukey.cld3)

$Trat
$Trat$Letters
  SS SCEL  SCT   SR 
 "a"  "a"  "a"  "a" 

$Trat$LetterMatrix
        a
SS   TRUE
SCEL TRUE
SCT  TRUE
SR   TRUE


$Ciclo
$Ciclo$Letters
  1   2   4   3 
"a" "a" "a" "a" 

$Ciclo$LetterMatrix
     a
1 TRUE
2 TRUE
4 TRUE
3 TRUE


$`Trat:Ciclo`
$`Trat:Ciclo`$Letters
  SS:2  SCT:1 SCEL:1   SS:1   SR:4 SCEL:3   SS:3 SCEL:4   SS:4 SCEL:2  SCT:3 
   "a"    "a"    "a"    "a"    "a"    "a"    "a"    "a"    "a"    "a"    "a" 
 SCT:2  SCT:4   SR:1   SR:2   SR:3 
   "a"    "a"    "a"    "a"    "a" 

$`Trat:Ciclo`$LetterMatrix
          a
SS:2   TRUE
SCT:1  TRUE
SCEL:1 TRUE
SS:1   TRUE
SR:4   TRUE
SCEL:3 TRUE
SS:3   TRUE
SCEL:4 TRUE
SS:4   TRUE
SCEL:2 TRUE
SCT:3  TRUE
SCT:2  TRUE
SCT:4  TRUE
SR:1   TRUE
SR:2   TRUE
SR:3   TRUE

data_summary3 = group_by(database, Trat, Ciclo) %>%
  summarise(mean=mean(CH4), sd=sd(CH4)) %>%
  arrange(desc(mean))

`summarise()` has grouped output by 'Trat'. You can override using the `.groups` argument.

print(data_summary3)

cld3 = as.data.frame.list(tukey.cld3$`Trat:Ciclo`)
data_summary3$Tukey = cld3$Letters
print(data_summary3)

Rodei tukey só para manter o padrão, mas o P valor da variancia não tinha sido significativo.

Plot

plot3=ggplot(data_summary3, aes(x = factor(Trat), y = mean, fill = Ciclo, colour = Ciclo)) + 
  geom_bar(stat = "identity", position = "dodge", alpha = 0.5) +
  geom_errorbar(aes(ymin=mean-sd, ymax=mean+sd), position = position_dodge(0.9), width = 0.25) +
  labs(x="Tratamentos", y="CH4")+ theme_bw() + 
  theme(panel.grid.major = element_blank(), panel.grid.minor = element_blank(),legend.position = c(0.2, 0.9),  legend.direction = "horizontal")+
  geom_text(aes(label=Tukey), position = position_dodge(0.90), size = 3, 
            vjust=-0.8, hjust=-0.5, colour = "Black")
plot3

4 - Importar graficos

library(cowplot) #importar graficos
side.by.side = plot_grid(plot1,plot2,plot3,labels = c("A", "B", "C"), ncol = 1, nrow = 3, align = "v")
side.by.side
save_plot("Plots Beatriz.pdf", side.by.side, ncol = 1, nrow = 3)

Os graficos serão salvos em pdf no mesmo lugar onde foi salvo o script.