Lecture 10A: Assessment of Measurement Validity Flashcards

1
Q

What is measurement validity?

A

A test is considered valid if it measures what it is intended to measure and is free from error

A valid test is also reliable.

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
2
Q

List the different types of measurement validity.

A
  • Face
  • Content
  • Construct
  • Concurrent
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
3
Q

What does face validity indicate?

A

The instrument appears to measure what it is supposed to measure

Usually established through direct observation.

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
4
Q

How is face validity assessed?

A

By direction observation, e.g. rulers. Assessed as all or none

It is considered the weakest type of validity.

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
5
Q

Define content validity.

A

The extent to which the measurement incorporates the domain of the phenomenon under study.

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
6
Q

What is an example of content validity?

A

Incorporating aspects of physical function such as feeding, dressing, walking, etc.

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
7
Q

How is content validity assessed?

A

During the planning stage, based on subjective judgment

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
8
Q

What is concurrent validity?

A

The measurement to be validated and the criterion measure are taken concurrently and compared.

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
9
Q

Which statistics are used to assess concurrent validity?

A

Pearson’s r or Spearman’s rho depending on the level of data.

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
10
Q

What indicates good concurrent validity?

A

A high correlation between the new test and the gold standard.

High r value = High concurrent validity

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
11
Q

What is construct validity?

A

The ability of an instrument to measure an abstract concept (construct).

e.g. quality of life

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
12
Q

What must be demonstrated to establish construct validity?

A
  • Convergent validity
  • Discriminant validity
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
13
Q

Define convergent validity.

A

Two measures believed to reflect the same characteristic should have high correlation.

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
14
Q

Define discriminant validity.

A

Two measures believed to assess different characteristics should have low correlation.

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
15
Q

What is an example of establishing convergent validity?

A

Correlate a new quality of life measure with another QOL measure and expect high correlation.

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
16
Q

What is an example of establishing discriminant validity?

A

Correlate a new quality of life measure with cognition or upper limb function and expect low correlation.

17
Q

What is the significance of Pearson’s r = 0.955?

A

Indicates excellent correlation and validity of the variables concerned

18
Q

What type of judgment is content validity based on?

A

Subjective judgment (expert panel).

19
Q

What is the relationship between validity and reliability?

A

A valid test is also reliable.

20
Q

How is face validity assessed?

A

Through direct observation of the instrument.

21
Q

True or False: A valid test does not need to be reliable.

22
Q

Fill in the blank: A test with _______ validity indicates it measures what it is supposed to measure.

23
Q

Fill in the blank: The extent to which the measurement incorporates the domain of the phenomenon under study defines _______.

A

content validity

24
Q

What should be the correlation expectation for convergent validity?

A

High correlation

25
Q

What should be the correlation expectation for discriminant validity?

A

Low correlation