Scaling variables
The next step is wrangling the data into a format that is easy to analyze. We will wrangle our data for the next few exercises.
A neat thing about R is that may operations are vectorized. It means that a single operation can affect all elements of a vector. This is often convenient.
The column Attitude
in lrn14
is a sum of 10 questions related to students attitude towards statistics, each measured on the Likert scale (1-5). Here we'll scale the combination variable back to the 1-5 scale.
This exercise is part of the course
Helsinki Open Data Science
Exercise instructions
- Execute the example codes to see how vectorized division works
- Use vector division to create a new column
attitude
in thelrn14
data frame, where each observation ofAttitude
is scaled back to the original scale of the questions, by dividing it with the number of questions.
Hands-on interactive exercise
Have a go at this exercise by completing this sample code.
#lrn14 is available
# divide each number in a vector
c(1,2,3,4,5) / 2
# print the "Attitude" column vector of the lrn14 data
lrn14$Attitude
# divide each number in the column vector
lrn14$Attitude / 10
# create column 'attitude' by scaling the column "Attitude"
lrn14$attitude <- "change me!"