UAS KOMSTAT

1. a

# Load dataset
data("airquality")

# Hitung statistik deskriptif
summary(airquality$Ozone)

##    Min. 1st Qu.  Median    Mean 3rd Qu.    Max.    NA's 
##    1.00   18.00   31.50   42.13   63.25  168.00      37

sd(airquality$Ozone, na.rm = TRUE) # Standar deviasi

## [1] 32.98788

1. b

# Scatter plot Wind vs Temp
plot(airquality$Wind, airquality$Temp,
     main = "Scatter Plot Wind vs Temp",
     xlab = "Wind",
     ylab = "Temperature",
     col = "blue",
     pch = 19)

# Load dataset
data("mtcars")

# Buat bar chart
barplot(table(mtcars$cyl),
        main = "Bar Chart of Cylinders",
        xlab = "Number of Cylinders",
        ylab = "Frequency",
        col = "lightblue")

# Tambahkan label jumlah setiap kategori
text(x = barplot(table(mtcars$cyl)), y = table(mtcars$cyl),
     label = table(mtcars$cyl), pos = 3, cex = 0.8, col = "darkblue")

3. a

# Load dataset
data("iris")

# Buat boxplot
boxplot(Petal.Width ~ Species, data = iris,
        main = "Boxplot of Petal.Width by Species",
        xlab = "Species",
        ylab = "Petal.Width",
        col = "lightgreen")

3. b

# Korelasi
correlation <- cor(iris$Sepal.Length, iris$Petal.Length)
print(paste("Korelasi antara Sepal.Length dan Petal.Length adalah", round(correlation, 2)))

## [1] "Korelasi antara Sepal.Length dan Petal.Length adalah 0.87"

3. c

# Scatter plot dengan warna berdasarkan Species
library(ggplot2)

ggplot(iris, aes(x = Sepal.Length, y = Sepal.Width, color = Species)) +
  geom_point() +
  geom_smooth(method = "lm", se = FALSE) +
  labs(title = "Scatter Plot Sepal.Length vs Sepal.Width",
       x = "Sepal Length",
       y = "Sepal Width") +
  theme_minimal()

## `geom_smooth()` using formula = 'y ~ x'

# Buat tabel kontingensi
tabel <- table(mtcars$vs, mtcars$am)

# Uji Chi-Square
chi_result <- chisq.test(tabel)

# Output hasil
print(chi_result)

## 
##  Pearson's Chi-squared test with Yates' continuity correction
## 
## data:  tabel
## X-squared = 0.34754, df = 1, p-value = 0.5555

5. a

# Buat model regresi
model <- lm(Temp ~ Solar.R, data = airquality)

# Ringkasan model
summary(model)

## 
## Call:
## lm(formula = Temp ~ Solar.R, data = airquality)
## 
## Residuals:
##      Min       1Q   Median       3Q      Max 
## -22.3787  -4.9572   0.8932   5.9111  18.4013 
## 
## Coefficients:
##              Estimate Std. Error t value Pr(>|t|)    
## (Intercept) 72.863012   1.693951  43.014  < 2e-16 ***
## Solar.R      0.028255   0.008205   3.444 0.000752 ***
## ---
## Signif. codes:  0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
## 
## Residual standard error: 8.898 on 144 degrees of freedom
##   (7 observations deleted due to missingness)
## Multiple R-squared:  0.07609,    Adjusted R-squared:  0.06967 
## F-statistic: 11.86 on 1 and 144 DF,  p-value: 0.0007518

5. b

# Scatter plot dengan garis regresi
plot(airquality$Solar.R, airquality$Temp,
     main = "Scatter Plot with Regression Line",
     xlab = "Solar.R",
     ylab = "Temp",
     pch = 19,
     col = "pink")

# Tambahkan garis regresi
abline(model, col = "darkgreen", lwd = 2)

5. c Interpretasinya sebagai berikut

• Variabel Solar.R memiliki pengaruh positif signifikan terhadap Temp dengan slope kecil (0.028).
• Kekuatan model rendah (𝑅*2 = 7.6%), sehingga prediksi Temp berdasarkan Solar.R kurang baik.
• Meskipun demikian, model tetap signifikan secara statistik. Untuk peningkatan akurasi, perlu mempertimbangkan variabel independen lain yang lebih berpengaruh terhadap Temp.