library(ggplot2)
  1. A. Menghitung statistika deskriptif(mean,median, standar deviasi)untuk variabel Ozone
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
  1. B. Membuat diagram pencar(scatter plot) untuk variable Wind dan Temp
ggplot(airquality, aes(x = Wind, y = Temp)) +
  geom_point() +
  labs(title = "Scatter Plot Wind vs Temp",
       x = "Wind",
       y = "Temperature") +
  theme_minimal()

2. Buat bar chart untuk variabel cyl dari dataset mtcars dan tambahkan label jumlah setiap kategori pada grafik

ggplot(mtcars, aes(x = factor(cyl))) +  
  geom_bar(fill = "skyblue") +
  geom_text(stat = "count", aes(label = ..count..), vjust = -0.5) + 
  labs(title = "Bar Chart Jumlah Mobil Berdasarkan Jumlah Silinder",
       x = "Jumlah Silinder (cyl)",
       y = "Jumlah Mobil") +
  theme_minimal()
## Warning: The dot-dot notation (`..count..`) was deprecated in ggplot2 3.4.0.
## ℹ Please use `after_stat(count)` instead.
## This warning is displayed once every 8 hours.
## Call `lifecycle::last_lifecycle_warnings()` to see where this warning was
## generated.

3.A Membuat boxplot untuk membandingkan petal.width berdasarkan variabel species

ggplot(iris, aes(x = Species, y = Petal.Width, fill = Species)) +
  geom_boxplot() +
  labs(title = "Boxplot Petal.Width Berdasarkan Spesies",
       x = "Species",
       y = "Petal Width") +
  theme_minimal()

3.B Hitung korelasi antara Sepal.Lenght dan Sepal.width

cor(iris$Sepal.Length,iris$Petal.Length)
## [1] 0.8717538

3.C Buat scatter plot antara Sepal.Length dan Sepal.Width dengan warna berbeda berdasarkan spesies dengan warna berbeda

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

4. Lakukan uji chi square untuk menguji hubungan antara dua variabel vs dan am dalam mtcars

chisq.test(mtcars$vs, mtcars$am)
## 
##  Pearson's Chi-squared test with Yates' continuity correction
## 
## data:  mtcars$vs and mtcars$am
## X-squared = 0.34754, df = 1, p-value = 0.5555

5.A. Tanpilan ringgakas model

model_regresi <- lm(vs ~ am, data = mtcars)
summary(model_regresi)
## 
## Call:
## lm(formula = vs ~ am, data = mtcars)
## 
## Residuals:
##     Min      1Q  Median      3Q     Max 
## -0.5385 -0.3684 -0.3684  0.4615  0.6316 
## 
## Coefficients:
##             Estimate Std. Error t value Pr(>|t|)   
## (Intercept)   0.3684     0.1159   3.180  0.00341 **
## am            0.1700     0.1818   0.935  0.35704   
## ---
## Signif. codes:  0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
## 
## Residual standard error: 0.505 on 30 degrees of freedom
## Multiple R-squared:  0.02834,    Adjusted R-squared:  -0.004049 
## F-statistic: 0.875 on 1 and 30 DF,  p-value: 0.357

5.B. Membuat scatter plot untuk garis regresi

ggplot(mtcars, aes(x = am, y = vs)) +
  geom_point(color = "blue", size = 3) + 
  geom_smooth(method = "lm", se = FALSE, color = "red", size = 1.5) +  
  labs(title = "Plot Regresi Linier: vs ~ am",
       x = "Transmisi (am: 0 = Automatic, 1 = Manual)",
       y = "Engine Shape (vs: 0 = V-Engine, 1 = Straight Engine)") +
  theme_minimal() +
  theme(legend.position = "none") 
## Warning: Using `size` aesthetic for lines was deprecated in ggplot2 3.4.0.
## ℹ Please use `linewidth` instead.
## This warning is displayed once every 8 hours.
## Call `lifecycle::last_lifecycle_warnings()` to see where this warning was
## generated.
## `geom_smooth()` using formula = 'y ~ x'

5.C Interpretasi hasil, termasuk koefisien regresi dan nilai R square Koefisien dari regresi variabel vs dan am dalam dataset mtcars adalah standar deviasi : 0,17 t value = 0,935 p value = 0,357 R square = 0,028