Sociology 220

1
Sociology 220

• Jan 16, 2009
• Prof. J. Brines
• MGH 231

2
Operationalization
3
Sociological Concepts that are Variables

• Gender
• Ethnicity
• Education
• Age
• Marital Status
• Socioeconomic Status
• Anomie (Durkheim)

4
Another 220 Synonym

• Indicator Measure
• Indicator/Measure A concrete item that
  indicates the values on a variable for a given
  research case.
• Q3 Gender? Male ? Female ?

5
Common formats for measures

• Q8 What is the last year of schooling you
  completed? ___________________
• Format Open Ended

6
Close-ended questions

• Q21 How strongly do you agree or disagree with
  the following statement? Circle the appropriate
  number.
• I often find myself doing things without a
  strong sense of purpose.
• 1 2 3 4 5
• Strongly Disagree Strongly Agree

7
Likert Item A special kind of close-ended measure

• Seven-point Likert item
• How do you feel about the principle of public
  financing for Presidential elections?
• 1 2 3 4 5 6 7
• Strongly Approve Strongly Disapprove

8
Variables and Measures

• Variables are Abstract Measures are Concrete
• Variable Measure
• Religiosity Frequency of Church
• Attendance
• Job Compensation Salary
• Pension

9
If we have a well-defined variable, how do we go
about choosing or creating a good measure?
10
Determine how the variable varies

• 1. Along a continuum
• intelligence
• not so much Einsteinian
• wealth
• none

11
Or

• 2. Categorically
• gender
• Female Male
• marital status
• Single Married Separated Divorced Widowed

12
Determine whether a variable is continuous or
categorical

• Examples
• Poverty?
• Education?
• Ethnicity?
• Religious affiliation?

13
Why do this?

• Deciding whether a variable is continuous or
  categorical helps determine the appropriate level
  of measurement for that variable.

14

• Variables Type of Variation Measures Level of
  Measurement
• Discrete (categorical choppy) Nominal
• Race/ethnicity
• Academic performance Ordinal
• happiness Interval
• Continuous Ratio

15
Nominal Measures

• Measures that are strictly categorical, where
  there is no meaningful rank or ordering among the
  categories
• Examples
• Region of residence (East, West, Midwest, South)
• True/False or Yes/No items

16
Ordinal measures

• Measures that are categorical, but where the
  categories are inherently orderable or can be
  ranked
• Highest educational degree completed
• Classic grading schemes (A,B,C,D,F)
• College class standing (freshman, sophomore,
  junior, senior)

17
Interval measures

• Measures that use a numeric scale, but that are
  artificially constructed and whose 0 value is
  not equal to the empty set
• Fahrenheit temperature scale (no true 0
  temperature, in the sense of temp being
  nonexistent).
• Likert scales
• IQ scores

18
Key difference between Ordinal and Interval
measures

• For ordinal measures, there is no uniform
  difference or distance between adjacent
  categories or values.
• For interval measures, the difference between
  adjacent values is considered to be uniform.

19
Examples

• Highest educational degree completed
• 1 Less than HS 2 HS degree 3 Post-secondary
  degree
• Ordinal or Interval?

20
Example

• Score on Likert Scale
• I have a lot of say on my job.
• 1 2 3 4 5
• Not at all Very true
• True
• Ordinal or Interval?

21
Ratio-level Measure

• Like interval measures, but where a 0 (or some
  other value at the lowest end of the scale)
  represents, at least in principle, a true empty
  set.
• Annual earned income
• of college credits earned
• Age

22
Examples Ordinal, Interval, or Ratio?

• SAT verbal test scores (these range from 300 to
  800)
• Q1 What was your familys income last year?
• 1 Less than 10,000
• 2 10,000-24,999
• 3 25,000-49,999
• 4 50,000-74,999
• 5 75,000 or more