URS 6806: Measurement
[Chapters covered in this section: 4]
Conceptualizing Variables
- Concept: A notion or a social observation [e.g. politeness, crime,
intelligence, unemployment]
- Dimension: A specific aspect of a concept [e.g. politeness could include
several dimensions: a reciprocal smile; opening the door for another person;
waving in recognition; indulging in small talk]
- Indicator: A sign of presence or absence of a concept.
- Operational definition of a Variable: A specific measurable concept [along
one or more dimensions]
Types of variables:
- Independent
- Dependent
- Constants
- Control variables
Link between variables
- Covariation of variables: Direct, Inverse, Non-linear
- Relationships between variables: Causal; Directional
- Criteria for causality:
- Correlation (cause and effect have some actual relationship)
- Time Order (cause precedes effect)
- Nonspurious (effect cannot be explained by a third plausible variable)
- Necessary and sufficient causes
Units of Analysis
- Individuals
- Social groups
- Organizations
- Social artifacts
- Issues with Unit of Analysis
- Ecological fallacy
- Reductionism
Measurement of Variables
- Nominal: Variables with characteristics of exhaustiveness and mutual
exclusiveness; labels or characteristics
- Ordinal: Variables with attributes that can have a logical rank order
- Interval: Variables with logical distances between attributes; not based
on a true zero point (e.g. Celsius degrees)
- Ratio: Variables with logical distances between attributes, but are based
on a true zero point
- Issues with measurement
- Reliability (stability; equivalence; internal consistency)
- Operational validity (face; content; criterion--concurrent/ predictive)
- Sensitivity