Evidence Based Practice: Reliability, Validity, Sensitivity/Specificity Error,

Question 1

What is Reliability?

Answer 1

The consistency of an instrument or measure.

• Extent of a research instrument to consistently have the same results when used in the same situation on repeated occasions.

Question 2

What is Intra-Rater Reliability?

Answer 2

Test performed by 1 person several times

• Consistency of result when measured by the same person

Question 3

What is Inter-Rater Reliability?

Answer 3

Test performed by 2 or more individuals, testing for one variable

• Consistency of Results when measured by different graders

Question 4

What is Test-Retest Reliability?

Answer 4

Same test on the same individual on two separate occasions

Question 5

What is Validity?

Answer 5

• Extent to which the instrument used measures exactly what it is supposed to measure

Question 6

Relationship between validity and reliability?

Answer 6

Measurement can be reliable without being valid.

However

Validity is associated with consistency, therefore must also be reliable (to be valid it must be reliable)

Question 7

What is Content Validity?

Answer 7

Extent to which a test accurately assesses what it is supposed to assess.

• Testing fall risk, therefore a test should be used to test balance such as the TUG

Question 8

What is Construct Reliability?

Answer 8

Test should measure what it is supposed to measure

• Goniometer should measure ROM only, nothing else
• “Construction = Tools”

Question 9

What is Concurrent Validity?

Answer 9

Test performed and compared to the GOLD standard.

• Heart rate measured by peripheral pulses compared with ECG readings
• Lachman’s test and MRI

Question 10

What is Face Validity?

Answer 10

What the test APPEARS to measure

• Does not consider gold standard
• Such as a survey

Question 11

What is a Type 1 Error?

Answer 11

False Positive:

• Incorrectly rejecting a true null hypothesis.

Question 12

What is a Type II Error?

Answer 12

False Negative:

• Failing to reject a false null hypothesis.

Question 13

What is Null Hypothesis?

Answer 13

Proposes that there is no statistical significance exists between variable/populations.

Question 14

What is Sensitivity?

Answer 14

Helps in ruling conditions “out” (SnOut)

• Sensitive Negative; Rule OUT
• Highly sensitive test has few false negatives
• If the Hawkins-Kennedy test is negative then we can rule out the condition.

Question 15

What is Specificity?

Answer 15

Helps in ruling conditions “in” (Spin)

• Specific Positive; Ruling In
• Highly specific test: Few False Positives