bangkitkan data kelas A

#bangkitkan data kelas b

set.seed(124)
kelas_B = round(rbeta(30, 60, 10)*100)
kelas_B
##  [1] 92 86 89 85 77 82 82 87 85 78 84 92 88 80 80 81 86 90 90 90 83 87 74 86 87
## [26] 85 89 89 89 86

bangkitkan data kelas c

set.seed(122)
kelas_C = round(rbeta(30, 60, 10)*100)
kelas_C
##  [1] 90 85 83 93 76 84 84 90 87 86 89 84 95 94 79 82 90 82 88 88 90 85 86 90 85
## [26] 83 77 83 90 88

statistika deskriptif

kelas A

#Mean
mean_kelasA <- mean(kelas_A)
cat("Mean Kelas A:", mean_kelasA,"\n")
## Mean Kelas A: 83.7
#Median
median_kelasA <- median(kelas_A)
cat("Median Kelas A:", median_kelasA, "\n")
## Median Kelas A: 85
#Variansi
var_kelasA <- var(kelas_A)
cat("Variansi Kelas A:", var_kelasA, "\n")
## Variansi Kelas A: 25.11379
# standar devisi
sd_kelasA <- sd(kelas_A)
cat("Standar Deviasi Kelas A:", sd_kelasA, "\n")
## Standar Deviasi Kelas A: 5.011366

Kelas B

#Mean 
mean_kelasB <- mean(kelas_B)
cat("Mean Kelas B:", mean_kelasB,"\n")
## Mean Kelas B: 85.3
#Median
median_kelasB <- median(kelas_B)
cat("Median Kelas B:", median_kelasB, "\n")
## Median Kelas B: 86
#Variansi
var_kelasB <- var(kelas_B)
cat("Variansi Kelas B:", var_kelasB, "\n")
## Variansi Kelas B: 20.07931
#Standar Deviasi
sd_kelasB <- sd(kelas_B)
cat("Standar Deviasi Kelas B:", sd_kelasB, "\n")
## Standar Deviasi Kelas B: 4.480994

kelas C

#Mean
mean_kelasC <- mean(kelas_C)
cat("Mean Kelas C:", mean_kelasC,"\n")
## Mean Kelas C: 86.2
#Median
median_kelasC <- median(kelas_C)
cat("Median Kelas C:", median_kelasC, "\n")
## Median Kelas C: 86
#Variansi
var_kelasC <- var(kelas_C)
cat("Variansi Kelas C:", var_kelasC, "\n")
## Variansi Kelas C: 21.2
#Standar Daeviasi
sd_kelasC <- sd(kelas_C)
cat("Variansi Kelas C:", sd_kelasC, "\n")
## Variansi Kelas C: 4.604346

Uji proporsi

prop.test(c(sum(kelas_A >= 75), sum(kelas_C >=75)), c(length(kelas_A),length(kelas_C)),alternative = "greater", correct = FALSE)
## Warning in prop.test(c(sum(kelas_A >= 75), sum(kelas_C >= 75)),
## c(length(kelas_A), : Chi-squared approximation may be incorrect
## 
##  2-sample test for equality of proportions without continuity correction
## 
## data:  c(sum(kelas_A >= 75), sum(kelas_C >= 75)) out of c(length(kelas_A), length(kelas_C))
## X-squared = 1.0169, df = 1, p-value = 0.8434
## alternative hypothesis: greater
## 95 percent confidence interval:
##  -0.08724024  1.00000000
## sample estimates:
##    prop 1    prop 2 
## 0.9666667 1.0000000

uji anava

nilai = c(kelas_A, kelas_B, kelas_C)
kelas = factor(rep(c("Kelas A","Kelas B", "Kelas C"), each=30))

anova_model = aov(nilai~kelas)
summary(anova_model)
##             Df Sum Sq Mean Sq F value Pr(>F)
## kelas        2   96.2   48.10   2.173   0.12
## Residuals   87 1925.4   22.13
TukeyHSD(anova_model)
##   Tukey multiple comparisons of means
##     95% family-wise confidence level
## 
## Fit: aov(formula = nilai ~ kelas)
## 
## $kelas
##                 diff        lwr      upr     p adj
## Kelas B-Kelas A  1.6 -1.2963353 4.496335 0.3894985
## Kelas C-Kelas A  2.5 -0.3963353 5.396335 0.1046936
## Kelas C-Kelas B  0.9 -1.9963353 3.796335 0.7398698

Visualisasi ANAVA

boxplot(nilai~kelas, data1=df,
       
        main="Boxplot Nilai Per Kelas",
        xlab="Kelas", ylab="Nilai",
        col=c("skyblue", "lightgreen", "pink"))

# visualisasi

# Kelas A
hist(kelas_A, col = "red",
     main= "Histogram Nilai Ujian Kelas A",
     xlab = "Nilai Ujian")

# kelas B
hist(kelas_B, col = "yellow",
     main= "Histogram Nilai Ujian Kelas B",
     xlab = "Nilai Ujian")

# Kelas C
hist(kelas_C, col = "green",
     main= "Histogram Nilai Ujian Kelas C",
     xlab = "Nilai Ujian")