KORELASI

Data

df <- read.csv("C:/Users/User/OneDrive/Dokumen/SEMESTER 6/Analisis Regresi/Data Projek/CrabAgePrediction.csv")
data <- df[c("Shell.Weight", "Age")]
head(data)

##   Shell.Weight Age
## 1     6.747181   9
## 2     1.559222   6
## 3     2.764076   6
## 4     5.244657  10
## 5     1.700970   6
## 6     7.229122   8

tail(data)

##      Shell.Weight Age
## 3888    9.0718400  11
## 3889    6.3786375   8
## 3890    9.7805775  10
## 3891    0.6378637   5
## 3892    2.9766975   6
## 3893    1.4174750   8

Statistik Deskriptif

cat("\n==== STATISTIK DESKRIPTIF ====\n")

## 
## ==== STATISTIK DESKRIPTIF ====

summary(data)

##   Shell.Weight           Age        
##  Min.   : 0.04252   Min.   : 1.000  
##  1st Qu.: 3.71378   1st Qu.: 8.000  
##  Median : 6.66213   Median :10.000  
##  Mean   : 6.79584   Mean   : 9.955  
##  3rd Qu.: 9.35534   3rd Qu.:11.000  
##  Max.   :28.49125   Max.   :29.000

Standar Deviasi

cat("\nStandar Deviasi Shell.Weight\n")

## 
## Standar Deviasi Shell.Weight

sd(data$Shell.Weight, na.rm = TRUE)

## [1] 3.943392

cat("\nStandar Deviasi Age\n")

## 
## Standar Deviasi Age

sd(data$Age, na.rm = TRUE)

## [1] 3.220967

Uji Korelasi

hasil_korelasi <- cor.test(data$Shell.Weight, data$Age, method = "pearson")
print(hasil_korelasi)

## 
##  Pearson's product-moment correlation
## 
## data:  data$Shell.Weight and data$Age
## t = 49.968, df = 3891, p-value < 2.2e-16
## alternative hypothesis: true correlation is not equal to 0
## 95 percent confidence interval:
##  0.6056761 0.6439620
## sample estimates:
##      cor 
## 0.625195

# Ambil p-value dan koefisien korelasi
p_value <- hasil_korelasi$p.value
r_value <- hasil_korelasi$estimate

cat("\nKoefisien Korelasi (r) =", round(r_value, 4), "\n")

## 
## Koefisien Korelasi (r) = 0.6252

cat("p-value =", round(p_value, 5), "\n")

## p-value = 0

# Keputusan uji (α = 0.05)
alpha <- 0.05

if (p_value < alpha) {
  cat("Keputusan: Tolak H0\n")
  cat("Kesimpulan: Terdapat korelasi yang signifikan antara Shell.Weight dan Age\n")
} else {
  cat("Keputusan: Gagal menolak H0\n")
  cat("Kesimpulan: Tidak terdapat korelasi yang signifikan antara Shell.Weight dan Age\n")
}

## Keputusan: Tolak H0
## Kesimpulan: Terdapat korelasi yang signifikan antara Shell.Weight dan Age

Scatterplot

# Membuat scatter plot 

plot(data$Shell.Weight, data$Age,
     main = "Scatter Plot Shell Weight vs Age", 
     xlab = "Shell Weight",
     ylab = "Age", 
     pch = 19, col = "blue")

# Menambahkan garis regresi 
abline(lm(data$Shell.Weight ~ data$Age), col = "red", lwd = 2)