Normality test for factor levels

Data
iris
Shapiro-Wilk test
H0 : the variable follow a normal distribution
H1 : the variable NOT follow a normal distribution

library(RVAideMemoire)

## *** Package RVAideMemoire v 0.9-80 ***

byf.shapiro(Sepal.Length~Species,data=iris)

## 
##  Shapiro-Wilk normality tests
## 
## data:  Sepal.Length by Species 
## 
##                 W p-value
## setosa     0.9777  0.4595
## versicolor 0.9778  0.4647
## virginica  0.9712  0.2583

OR

library(tidyverse)

## ── Attaching packages ─────────────────────────────────────── tidyverse 1.3.1 ──

## ✓ ggplot2 3.3.5     ✓ purrr   0.3.4
## ✓ tibble  3.1.5     ✓ dplyr   1.0.7
## ✓ tidyr   1.1.4     ✓ stringr 1.4.0
## ✓ readr   2.0.2     ✓ forcats 0.5.1

## ── Conflicts ────────────────────────────────────────── tidyverse_conflicts() ──
## x dplyr::filter() masks stats::filter()
## x dplyr::lag()    masks stats::lag()

library(rstatix)

## 
## Attaching package: 'rstatix'

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

iris %>%
  group_by(Species) %>%
  shapiro_test(Sepal.Length)

Sepal.Length variable for each groups :
p-value > 0.05 Accept H0,the p values are not statistically significant (the variable follow a normal distribution)

Q-Q plot using ggplot2

library(ggplot2)
library(qqplotr)

## 
## Attaching package: 'qqplotr'

## The following objects are masked from 'package:ggplot2':
## 
##     stat_qq_line, StatQqLine

ggplot(data = iris, mapping = aes(sample = Sepal.Length, fill = Species))+
  stat_qq_band(alpha=0.15) +stat_qq_line(alpha=0.15) +stat_qq_point(size=0.5) + facet_wrap(~ Species) +labs(title = "Normal Q-Q plot", x = "Theoretical Quantiles", y = "Sample Quantiles")+theme_bw()

Density plot using ggplot2
Using facet_wrap()

ggplot(data=iris,aes(x = Sepal.Length, fill = Species)) +
  geom_density(alpha=0.15)  +
  facet_wrap(Species ~ .)+theme_bw()

Using facet_grid()

ggplot(data=iris,aes(x = Sepal.Length, fill = Species)) +
  geom_density(alpha=0.15)  +
  facet_grid(Species ~ .)+theme_bw()

Multiple Overlay density plots using ggplot2

ggplot(data=iris, aes(x = Sepal.Length, fill = Species)) + 
  geom_density(alpha = 0.15)+labs(title = "Density plot with multiple groups")+theme_bw()

Histogram plot using ggplot2
Using facet_wrap()

ggplot(data = iris, aes(x = Sepal.Length,fill=Species)) +
  geom_histogram(alpha=0.15) +
  facet_wrap(Species ~ .)+theme_bw()

## `stat_bin()` using `bins = 30`. Pick better value with `binwidth`.

Using facet_grid()

ggplot(data = iris, aes(x = Sepal.Length,fill=Species)) +
  geom_histogram(alpha=0.15) +
  facet_grid(Species ~ .)+theme_bw()

## `stat_bin()` using `bins = 30`. Pick better value with `binwidth`.

Multiple Overlaid Histograms using ggplot2

ggplot(data = iris, aes(x = Sepal.Length,fill=Species)) +      
  geom_histogram(alpha = 0.15, position = "identity")+
  labs(title = "Histogram with multiple groups")+theme_bw()

## `stat_bin()` using `bins = 30`. Pick better value with `binwidth`.