Exploratory Data Analysis

LOADING PACKAGES

library(dplyr)

## 
## Attaching package: 'dplyr'

## The following objects are masked from 'package:stats':
## 
##     filter, lag

## The following objects are masked from 'package:base':
## 
##     intersect, setdiff, setequal, union

library(ggplot2)
library(ggpubr)

## Loading required package: magrittr

library(rstatix)

## 
## Attaching package: 'rstatix'

## The following object is masked from 'package:stats':
## 
##     filter

library(jmv)

LOADING DATA

Data <- iris3
View(Data)
Data <- as.data.frame(Data)
names(Data)

##  [1] "Sepal L..Setosa"     "Sepal W..Setosa"     "Petal L..Setosa"    
##  [4] "Petal W..Setosa"     "Sepal L..Versicolor" "Sepal W..Versicolor"
##  [7] "Petal L..Versicolor" "Petal W..Versicolor" "Sepal L..Virginica" 
## [10] "Sepal W..Virginica"  "Petal L..Virginica"  "Petal W..Virginica"

CLEANING DATA

Data_1 <- Data %>% 
  rename(Sepal_Length_Setosa = "Sepal L..Setosa",
         Sepal_Width_Setosa = "Sepal W..Setosa",
         Petal_Length_Setosa = "Petal L..Setosa",
         Petal_Width_Setosa = "Petal W..Setosa",
         Sepal_Length_Versicolor = "Sepal L..Versicolor",
         Sepal_Width_Versicolor = "Sepal W..Versicolor",
         Petal_Length_Versicolor = "Petal L..Versicolor",
         Petal_Width_Versicolor = "Petal W..Versicolor",
         Sepal_Length_Virginica = "Sepal L..Virginica",
         Sepal_Width_Virginica = "Sepal W..Virginica",
         Petal_Length_Virginica = "Petal L..Virginica",
         Petal_Width_Virginica = "Petal W..Virginica")

DESCRIPTIVES

Data_1 %>% select (Sepal_Length_Setosa, Sepal_Width_Setosa, Petal_Length_Setosa) %>% 
  descriptives(hist = TRUE,
               violin = TRUE, 
               dot = TRUE, dotType = "jitter", 
               qq = FALSE,
               n = TRUE, 
               missing = TRUE, 
               mean = TRUE, 
               median = TRUE,
               mode = TRUE, 
               sum = TRUE, 
               sd = TRUE, 
               variance = TRUE,
               range = FALSE, 
               min = TRUE, 
               max = TRUE, 
               se = FALSE,
               skew = TRUE, kurt = TRUE)

## 
##  DESCRIPTIVES
## 
##  Descriptives                                                                                
##  ------------------------------------------------------------------------------------------- 
##                           Sepal_Length_Setosa    Sepal_Width_Setosa    Petal_Length_Setosa   
##  ------------------------------------------------------------------------------------------- 
##    N                                       50                    50                     50   
##    Missing                                  0                     0                      0   
##    Mean                                  5.01                  3.43                   1.46   
##    Median                                5.00                  3.40                   1.50   
##    Mode                                  5.00                  3.40                   1.40   
##    Sum                                    250                   171                   73.1   
##    Standard deviation                   0.352                 0.379                  0.174   
##    Variance                             0.124                 0.144                 0.0302   
##    Minimum                               4.30                  2.30                   1.00   
##    Maximum                               5.80                  4.40                   1.90   
##    Skewness                             0.120                0.0412                  0.106   
##    Std. error skewness                  0.337                 0.337                  0.337   
##    Kurtosis                            -0.253                 0.955                   1.02   
##    Std. error kurtosis                  0.662                 0.662                  0.662   
##  -------------------------------------------------------------------------------------------

The function “descriptives()” is from package “jmv”

CORRELATIONS

cor_mat(Data_1)

## # A tibble: 12 x 13
##    rowname Sepal_Length_Se~ Sepal_Width_Set~ Petal_Length_Se~ Petal_Width_Set~
##  * <chr>              <dbl>            <dbl>            <dbl>            <dbl>
##  1 Sepal_~            1               0.74              0.27             0.28 
##  2 Sepal_~            0.74            1                 0.18             0.23 
##  3 Petal_~            0.27            0.18              1                0.33 
##  4 Petal_~            0.28            0.23              0.33             1    
##  5 Sepal_~           -0.081          -0.052            -0.13            -0.091
##  6 Sepal_~           -0.078          -0.14             -0.17            -0.025
##  7 Petal_~           -0.077          -0.06             -0.19            -0.04 
##  8 Petal_~            0.083           0.031            -0.15            -0.18 
##  9 Sepal_~            0.13           -0.076             0.15             0.075
## 10 Sepal_~            0.26            0.0061            0.13             0.096
## 11 Petal_~            0.17            0.056             0.1              0.011
## 12 Petal_~            0.28            0.1              -0.013            0.078
## # ... with 8 more variables: Sepal_Length_Versicolor <dbl>,
## #   Sepal_Width_Versicolor <dbl>, Petal_Length_Versicolor <dbl>,
## #   Petal_Width_Versicolor <dbl>, Sepal_Length_Virginica <dbl>,
## #   Sepal_Width_Virginica <dbl>, Petal_Length_Virginica <dbl>,
## #   Petal_Width_Virginica <dbl>

cor_plot(cor_mat(Data_1))

The End