Use LEFT and RIGHT arrow keys to navigate between flashcards;
Use UP and DOWN arrow keys to flip the card;
H to show hint;
A reads text to speech;
15 Cards in this Set
- Front
- Back
Measurement
|
Process of linking abstract concepts to empirical indicants—as a process for classifying the indicants in terms of the general concept in the researcher’s mind.
|
|
The Problem of Measurement
|
In social science , it is rare for researchers to be able to directly observe our concept so our measurement of a concept is almost always indirect.
•Therefore, measurement focuses on the relationship between the empirically grounded indicator (observable) and the underlying concept (unobservable) |
|
Reliability*
|
extent to which a procedure yields the same result on repeated trials
|
|
Validity*
|
extent to which an indicator of some abstract concept measures what it purports to measure
|
|
Sources of Unreliability
|
•Clerical errors (ex. data entry)
•Intentional error (“official statistics”) •Survey respondents may not understand the question or interpret differently from one another •Mood of the survey respondent •Concept may not be equivalent across contexts (satisfaction with democracy) |
|
Types of Validity: Content
|
Assesses degree to which the indicator represents the universe of content entailed in the systematized concept being measured.
ex.Can we even know the “universe of content”? |
|
Types of Validity: Criterion
|
Assess whether the scores produced by an indicator are empirically associated with scores for other criterion variables which are considered direct measures of the phenomenon of concern.
|
|
Types of Validity: Construct
|
Assessing whether a given indicator is empirically associated with other indicators in a way that conforms to theoretical expectations about heir inter-relationship
ex. if we think political engagement is linked to voter turnout, then if our indicator for political engagement ahs construct validity, it should be highly correlated with voter turnout. |
|
Reliability, Validity and Measurement Error
|
All measures are subject to error, either random or non-random
• X = t + e Where X = observed score, t = true score and e = error |
|
Random Error
|
•Chance factors that confound the measurement of any phenomenon.
•Inversely related to reliability –highly reliable measures have low random error. oReliable measures are free of random error but not necessarily free of non-random error |
|
Error, Reliability and Validity
|
All valid measures are reliable
Not all reliable measures are valid |
|
Levels of Measurement: Nominal
|
o Categories of a variable
o Tend to be dichotomous such as gender or religion o Measurement does not reveal anything about the relationship between categories |
|
Levels of Measurement: Ordinal
|
o Ranked categories like education or party identification (strong, moderate, weak)
o We still really don’t know how different the categories are |
|
Levels of Measurement: Interval
|
o Ranked categories with a common unit of measurement for the scale that enables comparisons across categories
|
|
Constitution
|
Shively defines a constitutions as a “set of rules by which power is distributed among the members” (209)
|