Deck 4: Outcome Properties

Question 1

Which is an example of ordinal data?

A) Blood pressure
B) Time
C) Cancer stage
D) Body weight

Answer 1

Cancer stage

Question 2

What do measures of dispersion help us with when looking at the data?

A) Finding the midpoint in a set of data
B) Ensuring reliability
C) Reducing a set of outcomes
D) Explaining the variance in the data

Answer 2

Explaining the variance in the data

Question 3

What is the definition of standard error of the measure?

A) The mathematical estimate of random measurement error
B) A measurement's variability as a result of random error
C) The mathematical estimate of the sampling error
D) Errors in measurement caused by factors that vary from one measurement to another

Answer 3

The mathematical estimate of random measurement error

Question 4

What is the definition of concurrent validity?

A) A measure of how well an outcome estimates a target value or gold stand measure
B) An outcome's ability to estimate a target value at the same time point
C) A measure in which two measuring devices or methods agree with each other
D) An outcome's ability to forecast an event in the future

Question 5

When measures do not center on the true score, this is the result of systematic error. What is the magnitude of the systematic error called?

A) Bias
B) Inaccuracy error
C) Divergent validity
D) Correlation error

Question 6

When is it more appropriate to use the median instead of the mean to calculate central tendency?

A) When nominal data has been collected
B) When there are data outliers
C) When a mode cannot be calculated
D) When ordinal data has been collected

Question 7

Which is NOT a type of measurement reliability?

A) Test-retest
B) Intersession
C) Intrarater
D) External consistency

Question 8

What is the problem with using the intraclass correlation coefficient?

A) It does not tell you whether a measure is repeatable.
B) It does not tell you the reliability of a measure.
C) It does not tell you how precise the measure is.
D) It does not tell you if the measurement is stable or consistent.

Question 9

Which is NOT a type of measurement validity?

A) Concurrent validity
B) Predicative validity
C) Divergent validity
D) Face validity

Question 10

Which is NOT true of criterion validity?

A) It is the most common form of validity used in exercise science and health care.
B) It refers to an outcome's ability to estimate a target value or "gold standard" outcome.
C) It can be established through factor analysis.
D) It is assessed by using the Pearson correlation coefficient.

Question 11

Which are examples of measures of dispersion? Select all that apply.

A) Random error
B) Standard deviation
C) Confidence interval
D) Measurement error

Question 12

Which are examples of types of measurement reliability? Select all that apply.

A) Intrarater
B) Test-retest
C) Intersession
D) Intrameasure

Question 13

Which is true of criterion validity? Select all that apply.

A) It is the most common form of validity used in exercise science and health care.
B) It refers to an outcome's ability to estimate a target value or "gold standard" outcome.
C) It can be established through factor analysis.
D) It is assessed by using the Pearson correlation coefficient.

Question 14

Which is a type of measurement validity? Select all that apply.

A) Concurrent validity
B) Predicative validity
C) Divergent validity
D) Face validity

Question 15

Which is true of factor analysis? Select all that apply.

A) It is particularly appropriate for establishing whether two measures of constructs that theoretically should be related are actually related.
B) It is a common method for establishing the construct validity of an outcome.
C) It is used to determine whether items on the questionnaire are related to each other and form groups of questions that are logically meaningful.
D) It is particularly appropriate for outcomes that include multiple items to establish them as meaningful constructs.

Question 16

Which are examples of clinimetric properties of measures? Select all that apply.

A) Minimal detectable change
B) Minimal difference
C) Minimal important difference
D) Receptiveness

Question 17

What are the limitations of the minimal important difference? Select all that apply.

A) The different methods for assessing minimal important difference can produce different values.
B) The monetary and time costs for the patient are rarely considered.
C) The minimal important difference depends on the post-treatment outcome.
D) The minimal important difference seldom considers the side effects of treatment.

Question 18

Which is true of the minimal important clinical difference? Select all that apply.

A) Minimal important clinical difference is developed from anchor measures the patient can report directly to the clinician.
B) Minimal important clinical difference is the smallest amount of change in an outcome that represents an important change to the clinician and perhaps the patient.
C) The methods for deriving the minimal clinical important difference are identical to those for calculating the minimal important difference.
D) The outcomes from the minimal important clinical difference may be of interest only to the practitioner because the practitioner recognizes a relationship that the patient does not.

Question 19

Other than the importance of reliability and validity for outcomes, there are other aspects to consider when it comes to putting research into practice. What are those characteristics? Select all that apply.

A) Floor and ceiling effects
B) Responsiveness
C) Minimal change
D) Interpretability

Question 20

The preferred measure for reporting sampling error is the standard deviation.

Question 21

An example of intrarater reliability is when a clinician measures blood pressure at baseline and 3-, 6-, and 9-months post-intervention.

Question 22

Convergent validity is a form of construct validity.

Question 23

A measure of central tendency that is the middle number in a sorted list is called the mode.

Question 24

The reliability coefficient is not only a useful measure for understanding whether a measure is repeatable, but also how precise the measure is.

Question 25

Using the mean to calculate central tendency is appropriate, except in the case when the data is skewed.

Question 26

A result is statistically significant if it has an alpha greater than or equal to 0.05.

Question 27

Construct validity is the most common form of validity in exercise science and health care.

Question 28

If both the predictor and outcome are measured at the same point, it is predictive validity.

Question 29

The definition of floor-to-ceiling effects is an outcome's inability to distinguish among subjects at the extreme ends of the scale.

Question 30

The following body mass indexes (BMIs) were taken: 25.2 kg/m², 19.5 kg/m², 30.1 kg/m², 24.2 kg/m², 20.5 kg/m², 24.2 kg/m², 18.3 kg/m², 18.9 kg/m², and 21.5 kg/m². Find the mode: _____________________________________________________________

Question 31

The following BMIs were taken: 25.2 kg/m², 19.5 kg/m², 30.1 kg/m², 24.2 kg/m², 20.5 kg/m², 24.2 kg/m², 18.3 kg/m², 18.9 kg/m², and 21.5 kg/m². Find the median: _____________________________________________________________

Question 32

The following BMIs were taken: 25.2 kg/m², 19.5 kg/m², 30.1 kg/m², 24.2 kg/m², 20.5 kg/m², 24.2 kg/m², 18.3 kg/m², 18.9 kg/m², and 21.5 kg/m². Find the mean: _____________________________________________________________

Question 33

The measure of central tendency representing the value that occurs most frequently is called ________________________.

Question 34

Errors in measurement caused by factors that vary from one measurement to another is called _________________________.

Question 35

The minimal amount of change between data points that must exist to ensure the change was not the result of measurement error is called ________________________.

Question 36

The statistical term that is the difference between the true score and the observed score is called ________________________.

Question 37

A measurement's variability resulting from random error measured by the standard error of the measure is called ________________________.