Research Methods: Chapter 3

Which of the following lists the scales of measurement in order from least to most informative?

Nominal, ordinal, interval, ratio

A student feedback form asks students to estimate how often class was cancelled. Results shows that estimates on this scale do not match the actual number of class cancellations. A follow-up showed that many students thought the question asked them how many times they skipped class and not how many times their professor cancelled class. Which of the following is an accurate description of the reliability and validity of this survey item measure?

The measure has low reliability and low validity.

Which of the following measures for distance has low face validity? The time of day of a commute The movement in inches of land following an earthquake The miles for a commute The space in feet between two people

The space in feet between two people (wrong) (maybe) The movement in inches of land following an earthquake

Which of the following is impossible?

a valid test is unreliable

Measurement that includes a large error component will have very low reliability. concurrent validity. face validity. all of the above

all of the above (wrong) (maybe) face validity

The construct validity of a measurement is the extent to which:

an operational definition for a variable or construct is actually measuring that variable or construct.

As a rule of thumb, a measure is considered sufficiently reliable if

at least half of the total variance is true-score variance

Which type of validity requires multiple research studies, usually conducted over a long period of time?

construct

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

convergent

The relationship between measurement error and reliability is inverse small curvilinear direct

direct (wrong) (maybe) inverse

A measure that does not correlate with measures with which it should not be related has

discriminant validity

A researcher developed a new intelligence test for elementary school children. However, the researcher fears that the scores from the test may actually be measuring the children's reading ability. To show that the test is really measuring intelligence and not reading ability, the researcher must demonstrate ________ validity.

divergent

Each of the following are interval scale measurements, except:

duration of sleep (in hours)

To identify the construct validity of a measure, we must: identify an appropriate statistical analysis needed to evaluate outcomes.

establish an appropriate operational definition for the construct being measured.

To test a measure's construct validity, researchers

examine its correlations with measures of related constructs

Researchers usually consider a measure to have adequate interitem reliability if Cronbach's alphacoefficient

exceeds .70

Which is the least important type of validity?

face

Which of the following tactics would not improve the reliability of a measure?

increase the error varience

The extent to which two or more raters of the same behavior or event are in agreement with what they observed, is called: .

inter-rater reliability

Two observers record similar measurements of behavior for a group of children they are watching. The researchers have established what kind reliability?

inter-rater reliability

Cronbach's alpha is a statistic used to quantify which measure of reliability?

internal consistency

Intelligence is measured on a(an) _________ scale.

interval

Distance is measured on a (an) scale. ordinal ratio interval nominal

interval (wrong) (maybe) ratio

A measure is valid inasmuch as:

it measures what it is intended to measure.

If participants' observed scores equal their true scores,

measurement error is zero

An animal researcher measures the number of times a rat presses a lever located at the right, center, and left of a cage for a food reward. What scale of measurement is the location of lever pressing?

nominal

Using letter grades (A, B, C, D, and F) to classify student performance on an exam is an example of measurement on a(n) _______ scale of measurement.

ordinal

Test-retest reliability is the extent to which scores are consistent:

over time

An EEG, heart rate, and brain activity are all examples of ________ measures.

physiological

Which type of measure tends to require sophisticated equipment?

physiological

You develop a new measure of honesty and you find that people who score high on your measure show more honest behavior than people who score low. You have demonstrated

predictive validity

All of the following is true regarding inter-rater reliability except: raters rate an observation consistently over time. raters give consistent ratings. raters agree with what they observed. raters rate an observation similarly.

raters agree with what they observed (wrong) (maybe) raters rate an observation similarly.

A researcher compares the amount of debt (in dollars) that undergraduate students incur to earn a four-year degree. College debt is on what scale of measurement?

ratio

Measuring a construct with several different kinds of measures is called

reliability

The proportion of total variance that is true score variance reflects a measure's

reliability

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

reliable

The criterion-related validity of a measurement is the extent to which:

scores obtained on some measure can be used to infer or predict an expected outcome.

If scores on a test are consistent over time, the test has

test-retest reliability

Establishing the reliability of a measurement procedure by using the procedure to measure the same individuals twice and comparing the two sets of scores is known as

test-retest reliability.

Each of the following is a type of validity, except:

test-retest validity.

The content validity of a measurement is the extent to which:

the items or contents of a measure adequately represent all the features of the construct being measured.

Test bias is demonstrated when predictive validity is better for one group than another the measure is reliable for one group but not for another convergent validity is the same for two different groups one group scores lower on the test than another group

the measure is reliable for one group but not for another (wrong) (maybe) predictive validity is better for one group than another

An ordinal scale of measurement is a measurement in which:

the scale conveys order or rank only.

A ratio scale of measurement is a measurement in which:

the scale has a true zero and is equidistant.

An interval scale of measurement is a measurement in which:

the scale has no true zero and is distributed in equal units.

What additional information is obtained by measuring on an ordinal scale compared to a nominal scale? the direction of the differences the size of the differences whether the measurements are the same or different none of the above

the size of the difference (wrong)

Concurrent validity is the extent to which: a measure can distinguish between groups it should be able to distinguish between. two or more different measures for the same construct are related. one measure can be differentiated from another measure that it should not be related to. scores obtained by a measure predict outcomes it should predict.

two or more different measures for the same construct are related. (wrong) (maybe) scores obtained by a measure predict outcomes it should predict.

For a measure to be reliable, it means that the measure is all of the following except:

valuable

Which of the following is an example of test-retest reliability?

A researcher showed that participant responses in a survey were consistent both times the assessment was completed.

Which of the following is an example of internal consistency?

A researcher shows that multiple items in a survey are measuring the same construct.