Lecture notes and solutions to the exercises of session 4 in the fall semester 2022

#T3 - Lecture notes (FaSe22)

 Lecture notes and solutions to the exercises of session 4 in the fall semester 2022
 

session_notes_4.R

# Lecture notes session 4

# Factors------------------------------
# Creating a factor
expl_fac <- factor(
  c("male", "male", "female"), 
  levels = unique(c("male", "female", "diverse"))
  )
expl_fac

# What happens if you create a factor that contains 
#  elements not contained in the levels-vector of the factor?
element_vec <- c("male", "male", "female")
level_vec <- c("female")
test_fac <- factor(
  x = element_vec, 
  levels = level_vec)
test_fac

# Test for factors:
typeof(test_fac) # Beware!!
is.factor(test_fac)

# Digression: types of measurement-----
# Make sure you recap the four levels of measurement:
#  Nominal: the data can only be categorized
#    Example: Gender, city of birth,...
#  Ordinal: the data can be categorized and ranked
#    Example: Language skill (A1, A2,...), responses to Likert skales,...
#  Interval: the data can be categorized, ranked, and evenly spaced
#    Example: Temperature (Celsius, Fahrenheit), IQ scales, ...
#  Ratio: the data can be categorized, ranked, evenly spaced, and has a natural zero.
#    Example: Temperature (Kelvin), age, height, income,...

# To store nominal data we usually use the type character or (unordered) factor
# To store ordinal data we use an ordered factor
# To store interval or ratio data we use doubles or integers

# Here is how you create an ordered factor:

ordered_factor <- factor(
  x = c("good", "okay", "bad", "good"), 
  ordered = TRUE)
ordered_factor # The sequence is strange, though...
# To change it specify the levels explicitly in the right sequence:
ordered_factor_right <- factor(
  x = c("good", "okay", "bad", "good"), 
  levels = c("bad", "okay", "good"),
  ordered = TRUE)
ordered_factor_right

# data.frames--------------------------
l_1 <- list(
  "column_1" = c(1, 2, 3, 4), 
  "column_2" = c("a", "b", "c")
)

df_1 <- data.frame(
  "column_1" = c(1, 2, 3), 
  "column_2" = c("a", "b", "c")
)
df_1

df_2 <- data.frame(
  "nb"=seq(1, 50),
  "ch"=rep("Hallo", 50)
)
str(df_2)

typeof(df_2$ch)

# Tibble
library(tibble)
df_1
tib_1 <- tibble::as_tibble(df_1)
tib_1