statistics and graphics
mohammad yasir roll no 151 (DS)
2024-01-07
R Markdown
Import your data into R
my_data <- iris
my_data## Sepal.Length Sepal.Width Petal.Length Petal.Width Species
## 1 5.1 3.5 1.4 0.2 setosa
## 2 4.9 3.0 1.4 0.2 setosa
## 3 4.7 3.2 1.3 0.2 setosa
## 4 4.6 3.1 1.5 0.2 setosa
## 5 5.0 3.6 1.4 0.2 setosa
## 6 5.4 3.9 1.7 0.4 setosa
## 7 4.6 3.4 1.4 0.3 setosa
## 8 5.0 3.4 1.5 0.2 setosa
## 9 4.4 2.9 1.4 0.2 setosa
## 10 4.9 3.1 1.5 0.1 setosa
## 11 5.4 3.7 1.5 0.2 setosa
## 12 4.8 3.4 1.6 0.2 setosa
## 13 4.8 3.0 1.4 0.1 setosa
## 14 4.3 3.0 1.1 0.1 setosa
## 15 5.8 4.0 1.2 0.2 setosa
## 16 5.7 4.4 1.5 0.4 setosa
## 17 5.4 3.9 1.3 0.4 setosa
## 18 5.1 3.5 1.4 0.3 setosa
## 19 5.7 3.8 1.7 0.3 setosa
## 20 5.1 3.8 1.5 0.3 setosa
## 21 5.4 3.4 1.7 0.2 setosa
## 22 5.1 3.7 1.5 0.4 setosa
## 23 4.6 3.6 1.0 0.2 setosa
## 24 5.1 3.3 1.7 0.5 setosa
## 25 4.8 3.4 1.9 0.2 setosa
## 26 5.0 3.0 1.6 0.2 setosa
## 27 5.0 3.4 1.6 0.4 setosa
## 28 5.2 3.5 1.5 0.2 setosa
## 29 5.2 3.4 1.4 0.2 setosa
## 30 4.7 3.2 1.6 0.2 setosa
## 31 4.8 3.1 1.6 0.2 setosa
## 32 5.4 3.4 1.5 0.4 setosa
## 33 5.2 4.1 1.5 0.1 setosa
## 34 5.5 4.2 1.4 0.2 setosa
## 35 4.9 3.1 1.5 0.2 setosa
## 36 5.0 3.2 1.2 0.2 setosa
## 37 5.5 3.5 1.3 0.2 setosa
## 38 4.9 3.6 1.4 0.1 setosa
## 39 4.4 3.0 1.3 0.2 setosa
## 40 5.1 3.4 1.5 0.2 setosa
## 41 5.0 3.5 1.3 0.3 setosa
## 42 4.5 2.3 1.3 0.3 setosa
## 43 4.4 3.2 1.3 0.2 setosa
## 44 5.0 3.5 1.6 0.6 setosa
## 45 5.1 3.8 1.9 0.4 setosa
## 46 4.8 3.0 1.4 0.3 setosa
## 47 5.1 3.8 1.6 0.2 setosa
## 48 4.6 3.2 1.4 0.2 setosa
## 49 5.3 3.7 1.5 0.2 setosa
## 50 5.0 3.3 1.4 0.2 setosa
## 51 7.0 3.2 4.7 1.4 versicolor
## 52 6.4 3.2 4.5 1.5 versicolor
## 53 6.9 3.1 4.9 1.5 versicolor
## 54 5.5 2.3 4.0 1.3 versicolor
## 55 6.5 2.8 4.6 1.5 versicolor
## 56 5.7 2.8 4.5 1.3 versicolor
## 57 6.3 3.3 4.7 1.6 versicolor
## 58 4.9 2.4 3.3 1.0 versicolor
## 59 6.6 2.9 4.6 1.3 versicolor
## 60 5.2 2.7 3.9 1.4 versicolor
## 61 5.0 2.0 3.5 1.0 versicolor
## 62 5.9 3.0 4.2 1.5 versicolor
## 63 6.0 2.2 4.0 1.0 versicolor
## 64 6.1 2.9 4.7 1.4 versicolor
## 65 5.6 2.9 3.6 1.3 versicolor
## 66 6.7 3.1 4.4 1.4 versicolor
## 67 5.6 3.0 4.5 1.5 versicolor
## 68 5.8 2.7 4.1 1.0 versicolor
## 69 6.2 2.2 4.5 1.5 versicolor
## 70 5.6 2.5 3.9 1.1 versicolor
## 71 5.9 3.2 4.8 1.8 versicolor
## 72 6.1 2.8 4.0 1.3 versicolor
## 73 6.3 2.5 4.9 1.5 versicolor
## 74 6.1 2.8 4.7 1.2 versicolor
## 75 6.4 2.9 4.3 1.3 versicolor
## 76 6.6 3.0 4.4 1.4 versicolor
## 77 6.8 2.8 4.8 1.4 versicolor
## 78 6.7 3.0 5.0 1.7 versicolor
## 79 6.0 2.9 4.5 1.5 versicolor
## 80 5.7 2.6 3.5 1.0 versicolor
## 81 5.5 2.4 3.8 1.1 versicolor
## 82 5.5 2.4 3.7 1.0 versicolor
## 83 5.8 2.7 3.9 1.2 versicolor
## 84 6.0 2.7 5.1 1.6 versicolor
## 85 5.4 3.0 4.5 1.5 versicolor
## 86 6.0 3.4 4.5 1.6 versicolor
## 87 6.7 3.1 4.7 1.5 versicolor
## 88 6.3 2.3 4.4 1.3 versicolor
## 89 5.6 3.0 4.1 1.3 versicolor
## 90 5.5 2.5 4.0 1.3 versicolor
## 91 5.5 2.6 4.4 1.2 versicolor
## 92 6.1 3.0 4.6 1.4 versicolor
## 93 5.8 2.6 4.0 1.2 versicolor
## 94 5.0 2.3 3.3 1.0 versicolor
## 95 5.6 2.7 4.2 1.3 versicolor
## 96 5.7 3.0 4.2 1.2 versicolor
## 97 5.7 2.9 4.2 1.3 versicolor
## 98 6.2 2.9 4.3 1.3 versicolor
## 99 5.1 2.5 3.0 1.1 versicolor
## 100 5.7 2.8 4.1 1.3 versicolor
## 101 6.3 3.3 6.0 2.5 virginica
## 102 5.8 2.7 5.1 1.9 virginica
## 103 7.1 3.0 5.9 2.1 virginica
## 104 6.3 2.9 5.6 1.8 virginica
## 105 6.5 3.0 5.8 2.2 virginica
## 106 7.6 3.0 6.6 2.1 virginica
## 107 4.9 2.5 4.5 1.7 virginica
## 108 7.3 2.9 6.3 1.8 virginica
## 109 6.7 2.5 5.8 1.8 virginica
## 110 7.2 3.6 6.1 2.5 virginica
## 111 6.5 3.2 5.1 2.0 virginica
## 112 6.4 2.7 5.3 1.9 virginica
## 113 6.8 3.0 5.5 2.1 virginica
## 114 5.7 2.5 5.0 2.0 virginica
## 115 5.8 2.8 5.1 2.4 virginica
## 116 6.4 3.2 5.3 2.3 virginica
## 117 6.5 3.0 5.5 1.8 virginica
## 118 7.7 3.8 6.7 2.2 virginica
## 119 7.7 2.6 6.9 2.3 virginica
## 120 6.0 2.2 5.0 1.5 virginica
## 121 6.9 3.2 5.7 2.3 virginica
## 122 5.6 2.8 4.9 2.0 virginica
## 123 7.7 2.8 6.7 2.0 virginica
## 124 6.3 2.7 4.9 1.8 virginica
## 125 6.7 3.3 5.7 2.1 virginica
## 126 7.2 3.2 6.0 1.8 virginica
## 127 6.2 2.8 4.8 1.8 virginica
## 128 6.1 3.0 4.9 1.8 virginica
## 129 6.4 2.8 5.6 2.1 virginica
## 130 7.2 3.0 5.8 1.6 virginica
## 131 7.4 2.8 6.1 1.9 virginica
## 132 7.9 3.8 6.4 2.0 virginica
## 133 6.4 2.8 5.6 2.2 virginica
## 134 6.3 2.8 5.1 1.5 virginica
## 135 6.1 2.6 5.6 1.4 virginica
## 136 7.7 3.0 6.1 2.3 virginica
## 137 6.3 3.4 5.6 2.4 virginica
## 138 6.4 3.1 5.5 1.8 virginica
## 139 6.0 3.0 4.8 1.8 virginica
## 140 6.9 3.1 5.4 2.1 virginica
## 141 6.7 3.1 5.6 2.4 virginica
## 142 6.9 3.1 5.1 2.3 virginica
## 143 5.8 2.7 5.1 1.9 virginica
## 144 6.8 3.2 5.9 2.3 virginica
## 145 6.7 3.3 5.7 2.5 virginica
## 146 6.7 3.0 5.2 2.3 virginica
## 147 6.3 2.5 5.0 1.9 virginica
## 148 6.5 3.0 5.2 2.0 virginica
## 149 6.2 3.4 5.4 2.3 virginica
## 150 5.9 3.0 5.1 1.8 virginica# Print the first 6 rows
head(my_data, 6)## Sepal.Length Sepal.Width Petal.Length Petal.Width Species
## 1 5.1 3.5 1.4 0.2 setosa
## 2 4.9 3.0 1.4 0.2 setosa
## 3 4.7 3.2 1.3 0.2 setosa
## 4 4.6 3.1 1.5 0.2 setosa
## 5 5.0 3.6 1.4 0.2 setosa
## 6 5.4 3.9 1.7 0.4 setosaDescriptive statistics for a single group
Measure of central tendency: mean, median, mode
# Compute the mean value
mean(my_data$Sepal.Length)## [1] 5.843333# Compute the median value
median(my_data$Sepal.Length)## [1] 5.8# Compute the mode
# install.packages("modeest")
#require(modeest)
#mfv(my_data$Sepal.Length)Measure of variablity
Range: minimum & maximum
# Compute the minimum value
min(my_data$Sepal.Length)## [1] 4.3# Compute the maximum value
max(my_data$Sepal.Length)## [1] 7.9# Range
range(my_data$Sepal.Length)## [1] 4.3 7.9quantile(my_data$Sepal.Length)## 0% 25% 50% 75% 100%
## 4.3 5.1 5.8 6.4 7.9quantile(my_data$Sepal.Length, seq(0, 1, 0.1))## 0% 10% 20% 30% 40% 50% 60% 70% 80% 90% 100%
## 4.30 4.80 5.00 5.27 5.60 5.80 6.10 6.30 6.52 6.90 7.90IQR(my_data$Sepal.Length)## [1] 1.3Variance and standard deviation
# Compute the variance
var(my_data$Sepal.Length)## [1] 0.6856935# Compute the standard deviation =
# square root of th variance
sd(my_data$Sepal.Length)## [1] 0.8280661Median absolute deviation
# Compute the median
median(my_data$Sepal.Length)## [1] 5.8# Compute the median absolute deviation
mad(my_data$Sepal.Length)## [1] 1.03782summary() function
summary(my_data$Sepal.Length)## Min. 1st Qu. Median Mean 3rd Qu. Max.
## 4.300 5.100 5.800 5.843 6.400 7.900stat.desc() function
install.packages(“pastecs”)
# Compute descriptive statistics
library(pastecs)## Warning: package 'pastecs' was built under R version 4.3.2res <- stat.desc(my_data[, -5])
round(res, 2)## Sepal.Length Sepal.Width Petal.Length Petal.Width
## nbr.val 150.00 150.00 150.00 150.00
## nbr.null 0.00 0.00 0.00 0.00
## nbr.na 0.00 0.00 0.00 0.00
## min 4.30 2.00 1.00 0.10
## max 7.90 4.40 6.90 2.50
## range 3.60 2.40 5.90 2.40
## sum 876.50 458.60 563.70 179.90
## median 5.80 3.00 4.35 1.30
## mean 5.84 3.06 3.76 1.20
## SE.mean 0.07 0.04 0.14 0.06
## CI.mean.0.95 0.13 0.07 0.28 0.12
## var 0.69 0.19 3.12 0.58
## std.dev 0.83 0.44 1.77 0.76
## coef.var 0.14 0.14 0.47 0.64Graphical display of distributions
Installation and loading ggpubr
install.packages(“ggplot2”)
install.packages(“ggpubr”)
library(ggpubr)## Warning: package 'ggpubr' was built under R version 4.3.2## Loading required package: ggplot2## Warning: package 'ggplot2' was built under R version 4.3.2Box plots
ggboxplot(my_data, y = "Sepal.Length", width = 0.5)
Histogram
gghistogram(my_data, x = "Sepal.Length", bins = 9,
add = "mean")## Warning: `geom_vline()`: Ignoring `mapping` because `xintercept` was provided.## Warning: `geom_vline()`: Ignoring `data` because `xintercept` was provided.
Q-Q plots
ggqqplot(my_data, x = "Sepal.Length")
Descriptive statistics by groups
Install ddplyr as follow:
install.packages(“dplyr”)
library(dplyr)## Warning: package 'dplyr' was built under R version 4.3.2##
## Attaching package: 'dplyr'## The following objects are masked from 'package:pastecs':
##
## first, last## The following objects are masked from 'package:stats':
##
## filter, lag## The following objects are masked from 'package:base':
##
## intersect, setdiff, setequal, uniongroup_by(my_data, Species) %>%
summarise(
count = n(),
mean = mean(Sepal.Length, na.rm = TRUE),
sd = sd(Sepal.Length, na.rm = TRUE)
)## # A tibble: 3 × 4
## Species count mean sd
## <fct> <int> <dbl> <dbl>
## 1 setosa 50 5.01 0.352
## 2 versicolor 50 5.94 0.516
## 3 virginica 50 6.59 0.636library("ggpubr")
# Box plot colored by groups: Species
ggboxplot(my_data, x = "Species", y = "Sepal.Length",
color = "Species",
palette = c("#00AFBB", "#E7B800", "#FC4E07"))
# Stripchart colored by groups: Species
ggstripchart(my_data, x = "Species", y = "Sepal.Length",
color = "Species",
palette = c("#00AFBB", "#E7B800", "#FC4E07"),
add = "mean_sd")
Frequency tables
Create some data
# Hair/eye color data
df <- as.data.frame(HairEyeColor)
hair_eye_col <- df[rep(row.names(df), df$Freq), 1:3]
rownames(hair_eye_col) <- 1:nrow(hair_eye_col)
head(hair_eye_col)## Hair Eye Sex
## 1 Black Brown Male
## 2 Black Brown Male
## 3 Black Brown Male
## 4 Black Brown Male
## 5 Black Brown Male
## 6 Black Brown Male# hair/eye variables
Hair <- hair_eye_col$Hair
Eye <- hair_eye_col$EyeSimple frequency distribution: one categorical variable
# Frequency distribution of hair color
table(Hair)## Hair
## Black Brown Red Blond
## 108 286 71 127# Frequency distribution of eye color
table(Eye)## Eye
## Brown Blue Hazel Green
## 220 215 93 64# Compute table and convert as data frame
df <- as.data.frame(table(Hair))
df## Hair Freq
## 1 Black 108
## 2 Brown 286
## 3 Red 71
## 4 Blond 127# Visualize using bar plot
library(ggpubr)
ggbarplot(df, x = "Hair", y = "Freq")
Two-way contingency table: Two categorical variables
tbl2 <- table(Hair , Eye)
tbl2## Eye
## Hair Brown Blue Hazel Green
## Black 68 20 15 5
## Brown 119 84 54 29
## Red 26 17 14 14
## Blond 7 94 10 16xtabs(~ Hair + Eye, data = hair_eye_col)## Eye
## Hair Brown Blue Hazel Green
## Black 68 20 15 5
## Brown 119 84 54 29
## Red 26 17 14 14
## Blond 7 94 10 16xtabs(~ Hair + Eye, data = hair_eye_col)## Eye
## Hair Brown Blue Hazel Green
## Black 68 20 15 5
## Brown 119 84 54 29
## Red 26 17 14 14
## Blond 7 94 10 16position dodge
ggbarplot(df, x = “Hair”, y = “Freq”, color = “Eye”, position = position_dodge(), palette = c(“brown”, “blue”, “gold”, “green”))
Multiway tables: More than two categorical variables
xtabs(~Hair + Eye + Sex, data = hair_eye_col)## , , Sex = Male
##
## Eye
## Hair Brown Blue Hazel Green
## Black 32 11 10 3
## Brown 53 50 25 15
## Red 10 10 7 7
## Blond 3 30 5 8
##
## , , Sex = Female
##
## Eye
## Hair Brown Blue Hazel Green
## Black 36 9 5 2
## Brown 66 34 29 14
## Red 16 7 7 7
## Blond 4 64 5 8ftable(Sex + Hair ~ Eye, data = hair_eye_col)## Sex Male Female
## Hair Black Brown Red Blond Black Brown Red Blond
## Eye
## Brown 32 53 10 3 36 66 16 4
## Blue 11 50 10 30 9 34 7 64
## Hazel 10 25 7 5 5 29 7 5
## Green 3 15 7 8 2 14 7 8Compute table margins and relative frequency
margin.table(x, margin = NULL) prop.table(x, margin = NULL)
Hair <- hair_eye_col$Hair
Eye <- hair_eye_col$Eye
# Hair/Eye color table
he.tbl <- table(Hair, Eye)
he.tbl## Eye
## Hair Brown Blue Hazel Green
## Black 68 20 15 5
## Brown 119 84 54 29
## Red 26 17 14 14
## Blond 7 94 10 16# Margin of rows
margin.table(he.tbl, 1)## Hair
## Black Brown Red Blond
## 108 286 71 127# Margin of columns
margin.table(he.tbl, 2)## Eye
## Brown Blue Hazel Green
## 220 215 93 64# Frequencies relative to row total
prop.table(he.tbl, 1)## Eye
## Hair Brown Blue Hazel Green
## Black 0.62962963 0.18518519 0.13888889 0.04629630
## Brown 0.41608392 0.29370629 0.18881119 0.10139860
## Red 0.36619718 0.23943662 0.19718310 0.19718310
## Blond 0.05511811 0.74015748 0.07874016 0.12598425# Table of percentages
round(prop.table(he.tbl, 1), 2)*100## Eye
## Hair Brown Blue Hazel Green
## Black 63 19 14 5
## Brown 42 29 19 10
## Red 37 24 20 20
## Blond 6 74 8 13