What is a Factor?

Factor variables are a fundamental concept in statistics and data analysis, often referred to as categorical variables. These variables differ from numerical variables in that they have a limited and fixed set of possible values. Examples of factor variables include blood type, currency, and nationality.

Conversely, variables such as monthly income, height, and price are typically not considered categorical due to their unlimited range of potential values. However, even these can be converted into categorical variables, a process we will explore in later chapters.

Before creating a factor variable, let's first create a vector of currencies:

# Vector of currencies

curr <- c('USD', 'EUR', 'AUD', 'NOK',

'CHF', 'EUR', 'AUD', 'EUR')

typeof(curr)


              1234
            
# Vector of currencies
curr <- c('USD', 'EUR', 'AUD', 'NOK', 
          'CHF', 'EUR', 'AUD', 'EUR')
typeof(curr)

In fact, a factor is a type of vector. To indicate to R that we are working with factor values, we use the factor() function and pass the relevant vector of values as an argument:

curr <- c('USD', 'EUR', 'AUD', 'NOK',

'CHF', 'EUR', 'AUD', 'EUR')

# Convert into factor

curr_f <- factor(curr)

curr_f


              12345
            
curr <- c('USD', 'EUR', 'AUD', 'NOK', 
          'CHF', 'EUR', 'AUD', 'EUR')
# Convert into factor
curr_f <- factor(curr)
curr_f

Upon execution, not only is the vector of values output, but we also see a line titled Levels:, which indicates all the distinct (unique) values the factor can take.

Tarea

Swipe to start coding

Imagine we conducted a survey on blood groups and received 26 responses, which are now stored in the blood vector. Here's what you need to do:

Display the values of the original vector blood.
Convert blood into a factor and assign it to the variable blood_gr.
Display the values of blood_gr.

Solución

# Initial vector. Please, do not change the code below

blood <- c("O+","A+","O-","O+","A+","A+","B+",

"B+","AB+", "B+","O+","B+","A+","A-",

"O+","B+","A-","AB+", "B-","O-","AB-",

"O+","O+","A+","O+","A+")

# Output initial vector

blood

# Convert blood vector into factor

blood_gr <- factor(blood)

# Output converted into factor vector

blood_gr

¿Todo estuvo claro?

¡Gracias por tus comentarios!

Sección 3. Capítulo 1