3.2 Example 1

  • High-quality projects depart from some clearly defined concepts.
  • Population: What is the population we want to learn about?
    • Germans; Swiss students
  • Sample: What is the sample we are using?
    • Random sample of germans; students in this class-room
  • Concept: What feature do we want to learn about?
    • Income (students): [Low = below 1500, High = above 1500]
  • Measure: How do we measure the concept?
    • Survey question (income): How high is your income?
  • Variable/scale: What does the variable look like?
    • Income: ..has values, e.g. 0 = “low” and 1 = “high”
  • Measurement process:
    • Assign values of our variable to individuals (each cell = particular value)
  • Data: Sample of individuals grouped according to values (cells)
  • Q: What is measurement error? Example?
  • Terminology: Unit vs. observation vs. unit of analysis3
Table .: Distribution of Income
some_data Freq
high income 5
low income 5



  • Discussion
    • Q: What do the tables show?
    • Q: What does a cell in those tables show?
    • Q: What is a missing value/NA? Where are they in the tables above?
    • Q: How would the data look like in a dataframe?
Table .: Joint distribution of Income/Gender
female male
high income 5 0
low income 2 3


Table .: Univariate distribution of education (2006)
Economics Political Science Sociology
2 2 16

  1. Unit = particular individual Peter; Observation = Peter’s income at t = February 2028; Unit of analysis = unit in our model (= observations) such as i = Peter, or i = Peter*time if we have more measurement values for Peter.