The flashcards below were created by user
on FreezingBlue Flashcards.
Concurrent Validity (p. 71)
Whether measure accurately relates to relevant current behavior.
A form of criterion-related validity that reflects the extent to which a mesure allows a researcher to distinguish between respondents at the time the measure is taken.
Construct Validity (p. 69)
Whether measure relates to other measures as it should.
The degree to which a measure of a particular construct correlates as expected with measures of other constructs.
Convergent Validity (p. 69)
Whether measure correlates to measures of related constructs appropriately.
Documenting the validity of a measure by showing that it correlates appropriately with measures of related constructs.
Converging Operations (p. 57)
Using several measurement approaches to measure a variable.
Correlation Coefficient (p. 63)
An index of the direction and magnitude of the relationship between two variables; Ranges from -1.00 to 1.00
Criterion-related Validity (p. 70)
Whether measure predicts meaningful differences in relavant behavior.
The extent to which a measure allows a researcher to distinguish among respondents on the basis of some behavioral criterion.
Cronbach's Alpha Coefficient (p. 65)
An index of interitem reliability.
Discriminant Validity (p. 69)
Showing measure doesn't correlate with measures of unrelated concepts.
Documenting the validity of a measure by showing that it does not correlate with measures of conceptually unrelated constructs.
Face Validity (p. 68)
Whether a measurement procedure measures what it is supposed to.
The extent to which a measurement procedure apperars to measure what it is supposed to measure.
Hypothecial Construct (p. 69)
Something that can't be observed directly but is proven by observable evidence.
An entity that cannot be directly observed but that is inferred on the basis of observable evidence.
Ex. intelligence, status, and anxiety are examples of hypothetical constructs.
Interitem Reliability (p. 63)
The consistency of responses on a set of related items.
The consistency of resondents' responses on a set of conceptually related items.
Interrater Reliability (p. 66)
Consistency across judges.
The degree to which the observations of two independent raters agree.
Correlation should be > .70
Interval Scale (p. 58)
A measure on which equal distances between scores represent equal differences in the property being measured.
Item-total Correlation (p. 64)
The correlation between each item & the sum of all other items.
The correlation between respondents' scores on one item on a scale & the sum of their responses on the remaining items; an index of interitem reliability.
Should be > .30
Measurement Error (p. 59)
The deviation of a participant's observed score from his or her true score.
Nominal Scale (p. 58)
A measure on which the numbers assigned to participants' characteristics are merely labels; participant sex is on a nominal scale, for example.
Observational Measure (p. 56)
Measuring behavior through observation.
A method of measuring behavior by directly observing participants.
Ordinal Scale (p. 58)
Numbers reflect rank order from highest to lowest.
A measure on which the number assigned to participants' responses reflect the rank order of participants from highest to lowest.
Physiological Measure (p. 56)
A measure of bodily activity.
In behvioral research, physiological measures generally are used to assess processes within the nervous system.
Predictive Validity (p. 71)
Whether measure accurately predicts relevant future behavior.
A form of criterion-related validity that reflects the extent to which a measure allows a reseacher to distinguish between reponsents at some time in the future.
Psychometrics (p. 57)
The study of psychological measurement.
Ratio Scale (p. 58)
Scores = real numbers
A measure on which scores possess all of the characteristics of real numbers.
Reliability (p. 59)
Whether a measuring technique is dependable.
The consistency or dependability of a measuring technique; reliability is inversely related to measurement error.
Scales of Measurement (p. 58)
The degree that scores obtained on a scale reflect real numbers.
Properties of a measure that reflect the degree to which scores obtained on that measure reflect the characteristic of real numbers.
Four scales of measurement: nominal, ordinal, interbal, and ratio.
Self-report Measure (p. 56)
A measure where participants provide information about themselves.
Ex. questionnaire or interview
Split-half Reliability (p. 65)
Correlation between two halves of a scale.
The correlation between resondents' scores on two halves of a single instrument; an index of interitem reliability.
Should be > .70
Test Bias (p. 73)
Charateristic of a test that isn't equally valid for all groups.
The charateristic of a test that is not equally valid for different groups of people.
Test-retest Reliability (p. 63)
The consistency of respondents' scores over time.
True Score (p. 59)
The score one would obtain if there was no measurement error.
The hypothetical score that a participant would obtain if the attribute being measured could be measured without error.
Validity (p. 67)
The extend a measurement procedure measures what it is supposed to measure.