UAS Komputasi Statistika

Menginput data airquality

data("airquality")

Menghitung mean, median, dan standar deviasi untuk variabel Ozone

mean(airquality$Ozone, na.rm = TRUE)

## [1] 42.12931

median(airquality$Ozone, na.rm = TRUE)

## [1] 31.5

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

## [1] 32.98788

Membuat scatter plot antara variabel wind dan temp

plot(airquality$Wind, airquality$Temp,
     main = "Scatter plot",
     xlab = "Wind",
     ylab = "Temp",
     pch = 19,
     col = "black")

Menginput data mtcars

data("mtcars")

Membuat bar chart untuk variabel cyl

library(ggplot2)
cyl_count <- as.data.frame(table(mtcars$cyl))
colnames(cyl_count) <- c("cyl", "count")
ggplot(cyl_count, aes(x = factor(cyl), y = count)) +
  geom_bar(stat = "identity", fill = "black") +  geom_text(aes(label = count), vjust = -0.5, size = 5) + labs(title = "Jumlah Mobil Berdasarkan Jumlah Silinder",
       x = "Jumlah Silinder (cyl)",
       y = "Jumlah Mobil") +
  theme_minimal()

Menginput data iris

data("iris")

Membuat boxplot untuk variabel petal.width berdasarkan variabel species

boxplot(Petal.Width ~ Species, data = iris,
        main = "Boxplot petal.width berdasarkan species",
        xlab = "petal.width",
        ylab = "species",
        col = "white")

Menghitung korelasi antara variabel sepal.length dan petal.length

korelasi <- cor(iris$Sepal.Length, iris$Petal.Length)

Menginterprestasi hasil uji korelasi

Setelah di uji menggunakan korelasi, 0.8717 ini menunjukkan bahwa terdapat hubungan positif antara sepal.length dan petal.length

Membuat scatter plot antara variabel sepal.length dan sepla.width berdasarkan spesies

ggplot(iris, aes(x = Sepal.Length, y = Sepal.Width, color = Species)) +
  geom_point(size = 3) + geom_smooth(method = "lm", se = FALSE) +  labs(title = "Scatter Plot",
       x = "Sepal Length",
       y = "Sepal Width") +
  theme_minimal() +  # Tema minimalis
  scale_color_manual(values = c("setosa" = "red", 
                                "versicolor" = "yellow", 
                                "virginica" = "green"))

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

Melakukan uji Chi-Square

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

Membangun model regresi linear sederhana

lm(Temp ~ Solar.R, data = airquality)

## 
## Call:
## lm(formula = Temp ~ Solar.R, data = airquality)
## 
## Coefficients:
## (Intercept)      Solar.R  
##    72.86301      0.02825

Menampilkan ringkasan model

summary(lm(Temp ~ Solar.R, data = airquality))

## 
## 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

Membuat Scatter plot dengan garis regresi

ggplot(airquality, aes(x = Solar.R, y = Temp)) +
  geom_point(color = "black", size = 2) + geom_smooth(method = "lm", col = "black") + labs(title = "Scatter Plot",
       x = "Solar Radiation (Solar.R)",
       y = "Temperature (Temp)") +
  theme_minimal()

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

## Warning: Removed 7 rows containing non-finite outside the scale range
## (`stat_smooth()`).

## Warning: Removed 7 rows containing missing values or values outside the scale range
## (`geom_point()`).