Data and Variables

Lecture 2

2024-05-16

Some logistics

Reminders

• Drop/add ends tomorrow
• Class does not meet Fridays–next meeting is Monday
• The course syllabus is online.

Slides

• Will be available on the website. Use your arrow keys to navigate.

Data and Variables

Sociological data

Sociological data: Qualitative

• Interpretations, stories, narratives, observations

• Uses:

  • deep understanding of particular cases, theory building, where measurement doesn’t work

• Methods:

  • interviews, ethnographies, content analysis, image analysis, etc

Sociological data: Quantitative (this class)

• Measured quantities. Counts, closed-ended surveys, proportions, outcomes.

• Uses:

  • Describing measurable things about the world, theory testing

• Methods/sources:

  • Surveys, administrative data, digital trace data, etc

EADA data (from last time)

• Equity in Athletics Data Analysis
• Participation, staffing, revenues, and expenditures for men’s and women’s college sports teams

Step 1: Data -> data frame

Observations

• Each instance that you observe data about (often 1 observation = 1 person, but not always)
• Rows in your data frame

Variables

• Aspects that can be different for different cases
• Columns in your data frame
• Values the variable can take are called response options (especially in the context of surveys)

Types of variables

Categorical

• Response options have names, not numbers
• Mathematical operations (addition, subtraction, division) do not make sense
• The book treats these subtypes as the same–we will too for math’s sake, but sometimes the difference does play into interpretations

Categorical: Nominal

• Simple categories
• Can’t say one category is “bigger” or “smaller” than another
• Examples: gender identity, race, ethnicity, economic sector

Categorical: Ordinal

• You can say that one is “bigger” or “more” than another
• Examples: education (no hs diploma, hs diploma, some college, 2 year degree, 4 year degree, advanced degree), income (low, middle, high)

Categorical: Binary

• Has just two levels: yes/no; present/not present
• Examples: has college degree/does not have college degree; not ever married/married

Numeric

• Response options are numbers where the values are meaningful (ie, not arbitrary)
• Mathematical operations (addition, subtraction, etc) make sense

Numeric: Continuous

• Any value within a range is possible–decimals are fine
• Examples: Temperature, height, elevation, stock price

Numeric: Discrete

• Only certain values (usually round numbers) “make sense” and are used
• Examples: Age, years of education

Exercise: EADA data variable types

• Determine the type of each variable in this data set.

For next time:

• Read the syllabus, if you haven’t already
• Email me your exercise answers