Chapter 5 - Measurement Concepts

Reactivity

A problem of measurement in which the measure changes the behavior being observed.

Test-Retest Reliability

A reliability coefficient determined by the correlation between scores on a measure given at one time with scores on the same measure given at a later time.

Split-Half Reliability

A reliability coefficient determined by the correlation between scores on half of the items on a measure with scores on the other half of a measure.

Ordinal Scale

A scale of measurement in which the measurement categories form a rank order along a continuum.

Nomial Scale

A scale of measurement with two or more categories that have no numerical (less than, greater than) properties.

Pearson Product-Moment Correlation Coefficient

A type of correlation coefficient used with interval and ratio scale data. In addition to providing information on the strengeth of relationship between two variables, it indicates the direction ( positive or negative) of the relationship.

Predictive validity is a type of face validity. A) True B) False

A) False

A commonly used indicator of inter-rater reliability is called Cohen's Kappa. A) True B) False

A) True

A reactive measure does not provide information on how a person would behave under natural circumstances. A) True B) False

A) True

A reliable measure yields consistent results. A) True B) False

A) True

Any measure has two components: a true score and measurement error. A) True B) False

A) True

Cronbach's alpha yields a value that represents the average of a number of correlation coefficients. A) True B) False

A) True

Ratio scales have an absolute zero point. A) True B) False

A) True

Standardized tests such as the GRE and LSAT are assumed to be high in predictive validity. A) True B) False

A) True

The test-retest reliability for intelligence should be very high. A) True B) False

A) True

A reliable measure yields a score that A) contains little measurement error. B) a low true score. C) a negative Pearson product-moment correlation coefficient. D) a negative Cronbach's alpha.

A) contains little measurement error.

Dr. L reviewed a measurement scale designed to measure extroversion and said that it appeared to measure extroversion. The measure has __________ validity. A) face B) internal C) convergent D) predictive

A) face

A correlation of 0.00 means that the two variables are __________. A) not related at all B) strongly related C) negatively related D) positively related

A) not related at all

A group of students took a cognitive development test on Monday and then took the same test again the following week. Most likely, researchers were assessing the __________ reliability of the measure. A) test-retest B) split-half C) odd-even D) inter-item

A) test-retest

Content Validity

An indicator of construct validity of a measure in which the content of the measure is compared to the universe of content that defines the construct.

Conbach's Alpha

An indicator of internal consistency reliability assessed by examining the average correlation of each item (question) in a measure with every other question.

Interrater Reliability

An indicator of reliability that examines the agreement of observations made by two or more raters (judges).

True Score

An individual's actual score on a variable being measured, as opposed to the score the individual obtained on the measure itself.

Which of the following indicates the strongest correlation? A) +0.48 B) -0.98 C) +0.55 D) -0.02

B) -0.98

__________ validity refers to the adequacy of the operational definition of variables. A) Operational B) Construct C) Measurement D) Reliable

B) Construct

A 20-item measure of depression would be classified as a ratio scale. A) True B) False

B) False

A common method measuring convergent validity is to study whether two or more groups of people differ on the measure in expected ways. A) True B) False

B) False

Face validity is sufficient to conclude that measure is valid. A) True B) False

B) False

For most measures, test-retest reliability should be at least .70. A) True B) False

B) False

In a nominal scale, numeric properties are literal. A) True B) False

B) False

Split-half reliability is the correlation of each item on a test with every other item. A) True B) False

B) False

In validity research, a behavior is called a(n) A) coefficient. B) criterion. C) alpha. D) ratio.

B) criterion

One question on a student survey asked respondents to indicate their grade point average by circling A, B, C, D, or F. This measure of grade point average is an example of a ___________ scale. A) nominal B) ordinal C) interval D) ratio

B) ordinal

A chemistry teacher reports test grades as 0 points (no items correct) to 50 points (all items correct). This is most clearly an example of a(n) _____ scale. A) nominal B) ratio C) interval D) ordinal

B) ratio

If participants change their behavior because they know their behavior is being measured, the measure is said to be __________. A) systematic B) reactive C) predictive D) conducive

B) reactive

When a measurement of a psychological variable is consistent or stable, it is __________. A) valid B) reliable C) reactive D) both a and c

B) reliable

Which of the following statements about test-retest reliability is FALSE? A) The reliability coefficient of a measure should be at least .80 before the measure is accepted as reliable. B) Sometimes test-retest reliability is artificially high because people remember how they answered the first time. C) Test-retest reliability is the best form of reliability measurement. D) Test-retest reliability is very useful if the variable being measured is expected to stay constant over time.

C) Test-retest reliability is the best form of reliability measurement.

Dr. Jones is interested in creating a shorter version of an existing questionnaire. How can she determine which items from the longer questionnaire should be removed? A) conduct a split-half reliability B) calculate Cronbach's alpha C) conduct an item-total correlation D) calculate Cohen's Kappa

C) conduct an item-total correlation

One way to assess the stability of measures is by computing a Pearson __________. A) coefficient criterion B) linear coefficient C) correlation coefficient D) coefficient of determination

C) correlation coefficient

When you read about reliability in an article, the correlation between two test scores will usually be referred to as the __________ coefficient. A) score B) internal C) reliability D) significance

C) reliability

Mary weighed herself and the scale reading was 120 pounds. A few minutes later she weighed herself again and the same scale showed she weighed 125 pounds. The scale is __________. A) reactive B) predictive C) unreliable D) invalid

C) unreliable

Internal consistency reliability is to Cronbach's alpha as interrater reliability is to A) Spearman-Brown reliability coefficient. B) Pearson product moment correlation coefficient. C) then item-total correlation. D) Cohen's Kappa.

D) Cohen's Kappa

__________ validity is demonstrated when a measure is NOT related to variables with which it should not be related. A) Convergent B) Concurrent C) Differentiation D) Discriminant

D) Discriminant

Which of the following is an indicator of the internal consistency reliability of a measure? A) split-half reliability B) Cronbach's alpha C) inter-rater reliability D) both a and b

D) both a and b

When two raters observe the same behaviors, the extent to which their observations are in agreement is called __________. A) split-half reliability B) Chronbach's alpha C) item-total correlations D) inter-rater reliability

D) inter-rater reliability

Bill goes out to a professor-rating website and gives his psychology teacher 2 of 4 stars. The star rating system used by this website is an example of a(n) _____ scale. A) nominal B) interval C) ratio D) ordinal

D) ordinal

Internal Consistency Reliability

Reliability assessed with data collected at one point in time with multiple measures of a psychological construct. A measure is reliable when the multiple measures provide similar results.

Predictive Validity

The construct validity of a measure is assessed by examining the ability of the measure to predict a future behavior.

Discriminant Validity

The construct validity of a measure is assessed by examining the extent to which scores on the measure are not related to scores on the conceptually unrelated measures.

Convergent Validity

The construct validity of a measure is assessed by examining the extent to which scores on the measure are related to scores on other measures of the same construct or similar constructs.

Concurrent Validity

The construct validity of a measure is assessed by examining whether groups of people differ on the measure in expected ways.

Item-total Correlation

The correlation between scores on individual items with the total score on all items of a measure.

Reliability

The degree to which a measure is consistent.

Measurement Error

The degree to which a measurement deviates from the true score value.

Construct Validity

The degree to which a measurement device accurately measures the theoretical construct it is designed to measure.

Face Validity

The degree to which a measurement device appears to accurately measure a variable.

Interval Scale

The scale of measurement in which the intervals between numbers on the scale are all equal in size.

Ratio Scale

The scale of measurement in which there is an absolute zero point, indicating an absence of the variable being measured. An implication is that ratios of numbers on a scale can be formed (generally, these are physical measures such as weight or timed measures such as duration or reaction time).