PSYC 311 Unit 3 Quiz

Demonstrating the grade point averages for a group of college students are positively related
to their SAT scores is a demonstration of predictive validity for the SAT. (T/F)

true

What kind of validity requires that a researcher create two different measures of the same
variable?

convergent

All validity evidence can be interpreted as ________ validity.

construct

Using shoe size as a measure of intelligence would produce measurements that have very high
test-retest reliability. (T/F)

true

Which of the following is not a measure that we can use to evaluate reliability?

t test

A(n) ________ measure produces similar results when the same individuals are measured
under identical conditions.

reliable

Demand characteristics are cues within a research study that suggest how the participants are
expected to behave or respond. (T/F)

true

Reliability is

the degree to which a measure yields consistent results.

The behavior observed in a research study may be very different from behavior in normal
circumstances because the participants modify their behavior when they know that they are being
studied. This problem is known as:

reactivity

_____ reliability is determined by assessing the degree of relationship between scores on two
equivalent tests.

parallel forms

classical test theory

e = X - T , any difference between an observed score and the true score is an error of measurement.

reliability is the square of the__

correlation between observed scores and true scores.

inter-rater reliability

The degree of agreement between two observers

test-retest reliability

The reliability estimate obtained by comparing the scores obtained from two successive measurements

parallel-forms reliability

When different versions of a measure are used for the test and retest

split-half reliability

The instrument is split in half and a separate score for each half is computed. The degree of consistency between the two scores is called the split-half reliability.

internal consistency

estimates the average of all possible split-half reliabilities that can be obtained from all of the possible ways to split a test in half

Cronbach's alpha

most commonly used coefficient of internal consistency

validity

the degree to which the measurement process measures the construct that it claims to measure

face validity

unscientific form of validity demonstrated when a measurement procedure superficially appears to measure what it claims to measure

concurrent validity

used when the researcher is developing a new measure of a construct. If the new measure is correlated with another well-established measure of the same construct, that's the evidence of concurrent validity.

predictive validity

demonstrated when scores obtained from a measure accurately predict behavior according to a theory

construct validity

the scores obtained from a measurement procedure behave exactly the same as the construct itself

convergent validity

the correlation between two measures of the same construct (used with already established measures)

divergent validity

weak or no relation between scores obtained from two different methods of measuring two different constructs

what is the relationship between validity and reliability?

if a study is valid, it must also be reliable. A study van be reliable, but that does not mean it is also valid (can be reliably wrong)

ceiling effect

all the scores are squeezed together at the high end

floor effect

all the scores cluster at the low end