Lecture 3

Question 1

Observations/Cases

Answer 1

the objects we collect
data on

Question 2

Unit of observation

Answer 2

the level of our observations in our dataset

Question 3

Variables

Answer 3

• Variables are “the pieces of information we collect on our units of observation” (Haan
  &Godley 2017, p.12).
• Any property that varies can potentially be a variable (Takes on two or more values)
• Variables should be both exhaustive and mutually exclusive
  Exhaustive: there should be enough categories composing the variables to classify every
  observation; every observation or case has to have a place to go
  Mutually exclusive: there is only one category suitable for each observation; one observation
  cannot fit into multiple categories; every observation must fit into only one category
• columns in data set

Question 4

2 Purposes/Types of Variables

Answer 4

1. Identification variables: variables that uniquely identify each observational unit
2. Characteristic or measurement variables: variables that describe properties of our observations

Best practice: identification variables should be the first column(s) in our dataset

Question 5

4 Levels of measurement

Answer 5

1. Nominal
2. Ordinal
3. Interval
4. Ratio

Question 6

Nominal variables

Answer 6

• Categorical
• There is no quantifiable difference between categories
• It is not possible to rank the categories
• Numeric values used to represent categories are not meaningful
  (do not imply anything about the magnitude or differences
  between categories)
• Numbers or symbols are assigned to the values of the variable for
  the purpose of classifying, naming, or labelling
• Often referred to as “qualitative”
• Example: sex, religion, political party, ethnicity

Question 7

Ordinal variables

Answer 7

• You can rank the categories from low
  to high, but not calculate the
  difference between them
• Many attitudes we measure are
  ordinal-level variables (level of
  agreement or satisfaction)
• Example: social class, education,
  but also often times we measure age
  and income on ordinal scales

Question 8

Interval/ratio

Answer 8

• Compare values not only in terms of which is larger or smaller
  but also in terms of how much larger or smaller one is compared
  with another
• Sometimes distinguish between variables with a natural zero
  point (zero means the absence of the property) (ratio) and those
  where zero is arbitrary, meaning there’s no true zero (interval)

Question 9

Dataset Codebook

Answer 9

• A codebook describes the contents, structure, and layout of a data
  collection.
• Should include a description of the study, variable names and
  descriptions
• may also include question wording (survey data), information about
  weights, summary statistics

Question 10

Tidy Data

Answer 10

Tidy data refers to data that is stored in the following format:
* Each observation is a row
* Each variable is a column
* Each type of observational unit is a table

Question 11

Five common problems that make for untidy data

Answer 11

• Column headers are values, not variable names.
• Multiple variables are stored in one column.
• Variables are stored in both rows and columns.
• Multiple types of observational units are stored in the same table.
• Data values about a single type of observational unit are spread out over
  multiple datasets.