Hands-on 4

Visual Statistical Analysis

pacman::p_load(ggstatsplot, tidyverse)

exam <- read_csv("../data/Exam_data.csv")

Rows: 322 Columns: 7
── Column specification ────────────────────────────────────────────────────────
Delimiter: ","
chr (4): ID, CLASS, GENDER, RACE
dbl (3): ENGLISH, MATHS, SCIENCE

ℹ Use `spec()` to retrieve the full column specification for this data.
ℹ Specify the column types or set `show_col_types = FALSE` to quiet this message.

set.seed(1234)

gghistostats(
  data = exam,
  x = ENGLISH,
  type = "bayes",
  test.value = 60,
  xlab = "English scores"
)

ggbetweenstats(
  data = exam,
  x = GENDER, 
  y = MATHS,
  type = "np",
  messages = FALSE
)

Warning in min(x): no non-missing arguments to min; returning Inf

Warning in max(x): no non-missing arguments to max; returning -Inf

ggbetweenstats(
  data = exam,
  x = RACE, 
  y = ENGLISH,
  type = "p",
  mean.ci = TRUE, 
  pairwise.comparisons = TRUE, 
  pairwise.display = "s",
  p.adjust.method = "fdr",
  messages = FALSE
)

Warning in min(x): no non-missing arguments to min; returning Inf

Warning in max(x): no non-missing arguments to max; returning -Inf

ggscatterstats(
  data = exam,
  x = MATHS,
  y = ENGLISH,
  marginal = FALSE,
  )

exam1 <- exam %>% 
  mutate(MATHS_bins = 
           cut(MATHS, 
               breaks = c(0,60,75,85,100))
)

ggbarstats(exam1, 
           x = MATHS_bins, 
           y = GENDER)

Reflection:

Learn how to retrieve more advanced statistical info from data.

Visualising Uncertainty

exam <- read_csv("../data/Exam_data.csv")

Rows: 322 Columns: 7
── Column specification ────────────────────────────────────────────────────────
Delimiter: ","
chr (4): ID, CLASS, GENDER, RACE
dbl (3): ENGLISH, MATHS, SCIENCE

ℹ Use `spec()` to retrieve the full column specification for this data.
ℹ Specify the column types or set `show_col_types = FALSE` to quiet this message.

my_sum <- exam %>%
  group_by(RACE) %>%
  summarise(
    n=n(),
    mean=mean(MATHS),
    sd=sd(MATHS)
    ) %>%
  mutate(se=sd/sqrt(n-1))

ggplot(my_sum) +
  geom_errorbar(
    aes(x=RACE, 
        ymin=mean-se, 
        ymax=mean+se), 
    width=0.2, 
    colour="black", 
    alpha=0.9, 
    size=0.5) +
  geom_point(aes
           (x=RACE, 
            y=mean), 
           stat="identity", 
           color="red",
           size = 1.5,
           alpha=1) +
  ggtitle("Standard error of mean maths score by rac")

Warning: Using `size` aesthetic for lines was deprecated in ggplot2 3.4.0.
ℹ Please use `linewidth` instead.