Descriptive Analysis

MASS Cats’ summary

library(MASS)
data(cats, package = "MASS")
View(cats)
str(cats)

'data.frame':   144 obs. of  3 variables:
 $ Sex: Factor w/ 2 levels "F","M": 1 1 1 1 1 1 1 1 1 1 ...
 $ Bwt: num  2 2 2 2.1 2.1 2.1 2.1 2.1 2.1 2.1 ...
 $ Hwt: num  7 7.4 9.5 7.2 7.3 7.6 8.1 8.2 8.3 8.5 ...

summary(cats)

 Sex         Bwt             Hwt       
 F:47   Min.   :2.000   Min.   : 6.30  
 M:97   1st Qu.:2.300   1st Qu.: 8.95  
        Median :2.700   Median :10.10  
        Mean   :2.724   Mean   :10.63  
        3rd Qu.:3.025   3rd Qu.:12.12  
        Max.   :3.900   Max.   :20.50  

hist(cats$Hwt)

boxplot(cats$Hwt)

library(ggplot2)
ggplot(cats, aes(sample = Hwt)) + stat_qq() + stat_qq_line()

Shapiro-Wilk normality test

?shapiro.test

shapiro.test(rnorm(n = 100, mean = 0, sd = 1))

    Shapiro-Wilk normality test

data:  rnorm(n = 100, mean = 0, sd = 1)
W = 0.97832, p-value = 0.09818

shapiro.test(runif(100, min = 1, max = 10))

    Shapiro-Wilk normality test

data:  runif(100, min = 1, max = 10)
W = 0.96753, p-value = 0.01436

shapiro.test(runif(3, min = 1, max = 10))

    Shapiro-Wilk normality test

data:  runif(3, min = 1, max = 10)
W = 0.8844, p-value = 0.3374

shapiro.test(cats$Hwt)

    Shapiro-Wilk normality test

data:  cats$Hwt
W = 0.96039, p-value = 0.0003654

Laptop Prices’ summary

https://www.kaggle.com/ionaskel/laptop-prices

df = read.csv("laptops.csv")
summary(df$Price_euros)

   Min. 1st Qu.  Median    Mean 3rd Qu.    Max. 
    174     599     977    1124    1488    6099 

boxplot(df$Price_euros)

library(moments)
skewness(df$Price_euros)

[1] 1.519114

shapiro.test(df$Price_euros)

    Shapiro-Wilk normality test

data:  df$Price_euros
W = 0.89382, p-value < 2.2e-16