Ch. 3 - The Measurement of Behaviour Flashcards
What are the three types of measures used in behavioural research?
Observational measures, physiological measures, and self-report measures.
What are observational measures?
Direct observation of behaviour.
When are physiological measures used?
When interested in the relation between bodily processes and behaviour.
What do self-report measures involve?
The replies people give to questionnaires and interviews.
What are the three categories of self-report measures?
Cognitive self-reports (think), affective self-reports (feel), and behavioural self-reports (act).
What are psychometrics?
The specialty dedicated to the study of psychological measurement.
What are converging operations (AKA triangulation)?
When different kinds of measures provide the same results.
What are the 4 scales of measurement from lowest to highest?
Nominal, ordinal, interval, and ratio.
What is a nominal scale of measurement?
Numbers that are assigned as labels. i.e., not real numbers, only to indicate attributes of participants.
What is an ordinal scale of measurement?
Involves the rank ordering of a set of behaviours or characteristics. i.e., tells us the relative order of participants on a particular dimension, does not indicate the distance between them.
What is an interval scale of measurement?
Equal differences between the numbers reflect equal differences between participants in the characteristics being measured.
What is a ratio scale of measurement?
A scale involving a true zero point and real numbers that can be added, subtracted, multiplied, and divided.
How is the scale of measurement determined?
It depends on the characteristic being assessed.
Given a choice, what scale of measurement do people prefer?
The highest level available.
What is reliability?
The consistency or dependability of a measuring technique.
What is true score?
The score that the participant would have obtained if our measure were perfect.
What is measurement error the result of?
Multiple factors that distort the observed score.
What ar the five major categories of factors that contribute to measurement error?
Transient states of the participant, stable attributes of the participant, situational factors in the research setting, characteristics of the measure itself.
At what percentage of systematic variance is a measure considered sufficiently reliable?
70% of total variance is systematic.
What are the three types of reliability?
Test-retest, interitem, and interrater.
What is test-retest reliability?
The consistency of participants’ responses over time.
What is the minimum correlation necessary to determine good test-retest reliability?
0.70
What does inter-item reliability assess?
The degree of consistency among the items on a scale.
When is inter-item reliability assessed?
When a measure contains multiple items measuring the same construct.
What is the minimum correlation necessary for each item in an inter-item reliability measure?
0.30 each.
What is the Cronbach’s Alpha coefficient?
A measure equivalent to the average of all possible split-half reliabilities.
When is inter-item reliability adequate?
When it is greater than 0.70
What is inter-rater reliability?
Involves the consistency among two or more researchers who observe and record participants’ behaviour.
What is validity?
The extent to which a measurement procedure actually measures what it is intended to measure.
What are the three main types of validity?
Face, construct, and criterion related.
What is face validity?
The extent to which a measure appears to measure what it’s supposed to measure.
What effect does high face validity have on the public?
It increases confidence in the findings.
Is face validity necessary for actual validity?
No. Not necessarily.
What is construct validity?
How much a measure relates as it should to other measures. E.g., correlations between measures in question.
What is convergent validity?
When measures correlate with measures that they should correlate with.
What is discriminant validity?
When measures do not correlate (or correlate weakly) with measures that it should not correlate with.
What is criterion-related validity?
The extent to which a measure allows us to distinguish among participants on the basis of a particular behavioural criterion.
What are the two types of criterion-related validity?
Concurrent validity and predictive validity.
What is concurrent validity?
The two measures are administered at roughly the same time.
What is predictive validity?
A measure’s ability to distinguish between people on a relevant behavioural criterion at some time in the future.