A. PERSIAPAN

A.1 Instalasi Package R yang diperlukan

# Menentukan Lokasi Mirror, di Indonesia ada di BPPT
r <- getOption("repos")
r["CRAN"] <- "https://repo.bppt.go.id/cran/"
options(repos = r)

# Nama Package yang diperlukan
packages <- c('readxl', 'car','lme4','lsmeans')

# Fungsi Cek Apakah Package ada? Jika tidak ada, maka Install. Jika Sudah Di install maka Load!
for (p in packages){
  if(!require(p, character.only = T)){
    install.packages(p)
  }
  library(p,character.only = T)
}
## Loading required package: readxl
## Loading required package: car
## Loading required package: carData
## Loading required package: lme4
## Loading required package: Matrix
## Registered S3 methods overwritten by 'lme4':
##   method                          from
##   cooks.distance.influence.merMod car 
##   influence.merMod                car 
##   dfbeta.influence.merMod         car 
##   dfbetas.influence.merMod        car
## Loading required package: lsmeans
## Loading required package: emmeans
## The 'lsmeans' package is now basically a front end for 'emmeans'.
## Users are encouraged to switch the rest of the way.
## See help('transition') for more information, including how to
## convert old 'lsmeans' objects and scripts to work with 'emmeans'.

A.2 Data

Silahkan unduh data yang diperlukan KLIK SINI untuk DOWNLOAD Data Two Way Anova. Lalu tempatkan pada Folder yang sesuai. Kalau di Tutorial ini, diletakkan di Drive E dengan nama Folder R

B. TWO WAY ANOVA TANPA INTERAKSI

B.1 Akses R ke Data

Data yang akan digunakan berada pada Sheet TanpaInteraksi

library("readxl")
TanpaInteraksi <- read_excel("E:\\R\\Data Two Way Anova.xlsx", sheet = "TanpaInteraksi")

B.2 Melihat Data

# Melihat Data
TanpaInteraksi
## # A tibble: 20 x 3
##    Perlakuan Blok  Waktu
##    <chr>     <chr> <dbl>
##  1 MT1       B1       12
##  2 MT1       B2        2
##  3 MT1       B3        8
##  4 MT1       B4        1
##  5 MT1       B5        7
##  6 MT2       B1       20
##  7 MT2       B2       14
##  8 MT2       B3       17
##  9 MT2       B4       12
## 10 MT2       B5       17
## 11 MT3       B1       13
## 12 MT3       B2        7
## 13 MT3       B3       13
## 14 MT3       B4        8
## 15 MT3       B5       14
## 16 MT4       B1       11
## 17 MT4       B2        5
## 18 MT4       B3       10
## 19 MT4       B4        3
## 20 MT4       B5        6
# Melihat Struktur Data
str(TanpaInteraksi)
## tibble [20 x 3] (S3: tbl_df/tbl/data.frame)
##  $ Perlakuan: chr [1:20] "MT1" "MT1" "MT1" "MT1" ...
##  $ Blok     : chr [1:20] "B1" "B2" "B3" "B4" ...
##  $ Waktu    : num [1:20] 12 2 8 1 7 20 14 17 12 17 ...

B.3 Eksplorasi Data

library(car)
boxplot(Waktu~Perlakuan,TanpaInteraksi)

boxplot(Waktu~Blok,TanpaInteraksi)

B.4 Two Way Anova Tanpa Interaksi

library(lme4)
TwoWayAnovaTI <- lm(Waktu ~ Perlakuan+Blok, data = TanpaInteraksi)
anova(TwoWayAnovaTI)
## Analysis of Variance Table
## 
## Response: Waktu
##           Df Sum Sq Mean Sq F value    Pr(>F)    
## Perlakuan  3    310  103.33  51.667 3.911e-07 ***
## Blok       4    184   46.00  23.000 1.489e-05 ***
## Residuals 12     24    2.00                      
## ---
## Signif. codes:  0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1

B.5 Uji Lanjut

TukeyHSD(aov(TwoWayAnovaTI), "Perlakuan")
##   Tukey multiple comparisons of means
##     95% family-wise confidence level
## 
## Fit: aov(formula = TwoWayAnovaTI)
## 
## $Perlakuan
##         diff        lwr       upr     p adj
## MT2-MT1   10   7.344534 12.655466 0.0000006
## MT3-MT1    5   2.344534  7.655466 0.0005896
## MT4-MT1    1  -1.655466  3.655466 0.6858866
## MT3-MT2   -5  -7.655466 -2.344534 0.0005896
## MT4-MT2   -9 -11.655466 -6.344534 0.0000018
## MT4-MT3   -4  -6.655466 -1.344534 0.0036697
TukeyHSD(aov(TwoWayAnovaTI), "Blok")
##   Tukey multiple comparisons of means
##     95% family-wise confidence level
## 
## Fit: aov(formula = TwoWayAnovaTI)
## 
## $Blok
##       diff         lwr        upr     p adj
## B2-B1   -7 -10.1874323 -3.8125677 0.0001147
## B3-B1   -2  -5.1874323  1.1874323 0.3221545
## B4-B1   -8 -11.1874323 -4.8125677 0.0000305
## B5-B1   -3  -6.1874323  0.1874323 0.0686145
## B3-B2    5   1.8125677  8.1874323 0.0023287
## B4-B2   -1  -4.1874323  2.1874323 0.8504543
## B5-B2    4   0.8125677  7.1874323 0.0124195
## B4-B3   -6  -9.1874323 -2.8125677 0.0004858
## B5-B3   -1  -4.1874323  2.1874323 0.8504543
## B5-B4    5   1.8125677  8.1874323 0.0023287

C. TWO WAY ANOVA DENGAN INTERAKSI

C.1 Akses R ke Data

Data yang akan digunakan berada pada Sheet DenganInteraksi

library("readxl")
DenganInteraksi <- read_excel("E:\\R\\Data Two Way Anova.xlsx", sheet = "DenganInteraksi")

C.2 Melihat Data

# Melihat Data
DenganInteraksi
## # A tibble: 8 x 4
##   Pupuk Jagung Ulangan Hasil
##   <chr> <chr>    <dbl> <dbl>
## 1 P1    J1           1    28
## 2 P1    J1           2    30
## 3 P1    J2           1    42
## 4 P1    J2           2    38
## 5 P2    J1           1    33
## 6 P2    J1           2    33
## 7 P2    J2           1    40
## 8 P2    J2           2    42

C.3 Eksplorasi Data

# BoxPlot
library(car)
boxplot(Hasil~Pupuk,DenganInteraksi)

boxplot(Hasil~Jagung,DenganInteraksi)

# Plot interaksi
with(DenganInteraksi, interaction.plot(Pupuk, Jagung, Hasil))

C.4 Two Way Anova Dengan Interaksi

library(lme4)
TwoWayAnovaDI <- lm(Hasil ~ Jagung+Pupuk+Pupuk*Jagung, data = DenganInteraksi)
anova(TwoWayAnovaDI)
## Analysis of Variance Table
## 
## Response: Hasil
##              Df Sum Sq Mean Sq F value   Pr(>F)   
## Jagung        1  180.5   180.5 60.1667 0.001489 **
## Pupuk         1   12.5    12.5  4.1667 0.110787   
## Jagung:Pupuk  1    4.5     4.5  1.5000 0.287864   
## Residuals     4   12.0     3.0                    
## ---
## Signif. codes:  0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1

C.5 Uji Lanjut

#library(lsmeans)
#marginal.interaksi = lsmeans(TwoWayAnovaDI,
#                      pairwise ~ Pupuk:Jagung,
#                      adjust="tukey") 
#marginal.interaksi 
#TukeyHSD(aov(TwoWayAnovaDI), "Pupuk")
TukeyHSD(aov(TwoWayAnovaDI), "Jagung")
##   Tukey multiple comparisons of means
##     95% family-wise confidence level
## 
## Fit: aov(formula = TwoWayAnovaDI)
## 
## $Jagung
##       diff      lwr      upr     p adj
## J2-J1  9.5 6.099548 12.90045 0.0014905