Descriptive Statistics

Self-Assessment Questions2

  1. How can we distinguish between an attribute and a predictor?
  2. Why are descriptive statistics useful?
  3. Why do we need measures of centrality and spread?
  4. Why is the standard deviation more useful as a statistic than the deviation?
  5. Why is the sum of deviations always equal to zero?

Please stop here and don’t go beyond this point until we have compared notes on your answers.

Calculations

Data Set

Table 1: Data Set
i income age
1 450 21
2 550 23
3 300 27
4 650 30
5 100 20
6 900 18
7 200 20
8 250 22
9 300 21
10 600 21

Exercises

Calculate the following descriptive statistics for each variable:

  • Mean
  • Mode
  • Median
  • Range
  • Standard Deviation
  • Variance

Homework for Week 5

  • Finish and submit your summative report
  • Read the items marked “essential” on the reading list (see Talis).
  • In the seminars we will start working with R in Week 5. Please ensure that you do the following BEFORE coming to the seminar:
    • Download R and RStudio, following these instructions.
    • There is no need to go any further than the installation. We will cover the rest of the worksheet in the seminar.
    • Should you be prompted to install “developer tools”, please press “yes”. But make sure you are on a good internet connection and that you have a little time. Galaxies have formed and collapsed in less time…

Solutions

You can find the Solutions here or in the Downloads Section.

  1. Some of the content of this worksheet is taken from Reiche (forthcoming).↩︎