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;
17 Cards in this Set
- Front
- Back
way to measure variables- questionnaires, interviews
|
self-report measures
|
|
way to measure variables- biological data, requires special equipment
|
physiological measures
|
|
no special order of levels within variable. ex: gender, ethnicity, political party
|
nominal/categorical
|
|
rank order of levels, not necessarily equal distant apart
|
ordinal
|
|
numbers are equally distant, no true zero. ex: IQ, temperature
|
interval
|
|
numbers are equally distant, true zero. ex: weight, income
|
ratio
|
|
type of reliability: consistent measure or score every time for the same person
|
test-retest reliability
|
|
type of reliability: Consistent measure or score for two independent raters/observers
|
interrater reliability
|
|
type of reliability: Consistent pattern of responses across multiple items (e.g., questions in a questionnaire)
|
internal reliability
|
|
two subjective types of validity
|
face and content validity
|
|
4 criterion-related validities
|
Predictive validity
Concurrent validity Convergent validity Discriminant validity |
|
measurement validity: Does it look like it would be a good measure of what it’s supposed to measure?
Weak way to determine construct validity |
face validity
|
|
measurement validity: Does it capture all components or dimensions of the construct?
And are the elements within a measure relevant and representative of the construct? |
content validity
|
|
measurement validity: Is the measure associated with a future measure that it should be related to?
Test now predicts criterion assessed later |
predictive validity
|
|
measurement validity: Is the measure associated with a current measure that it should be related to?
Test now predicts criterion assessed at the same time |
concurrent validity
|
|
measurement validity: The measure should correlate more strongly with other measures of the same construct
|
convergent validity
|
|
measurement validity: The measure should correlate less strongly with measures of other, distinct constructs
|
divergent validity
|