Topic 3

Question 1

What is the meaning of ‘normal’

Answer 1

1. Within a range extending from 2 standard deviations below the mean to 2 standard deviations above or below the mean, or between specified percentiles of the distribution
2. In good health, indicative or pre-indicative of good health–> for a diagnostic screening test normal is one in a range within the probability of a specific disease is low
3. A normal Guassian distribution
   slide 5

Question 2

Whats the difference between hard and soft data?

Answer 2

-Hard is data that are reliable and preferably dimensional (e.g. lab data, demographic data, economic costs)

Soft- clinical performance like history taking, orthopaedic tests and other data like familial data
-subjective statements usually expressed in words rtahre than numbers by the people and the observers.

Question 3

What is reliability?

What does Kappa value mean?

Answer 3

Degrees to which the results obtained by a measurement procedure can be replicated under identical conditions.
-lack of reliability could be from instruments or the observers which is measuring.

It is the level of agreement beyond chance.
-the level of agreement by the same observer is intra-rater reliability
-The level of agreement between observers is known as intra-rater reliability. 1 is good.
Possible to achieve negative Kappa, the level of agreement is less than chance alone

Question 4

What is Validity?

Answer 4

Is the method sound.

That the study design is such that we can have confidence that it sets out to do what it claims to do.

Question 5

What is internal validity?

external validity?

Answer 5

Internal Validity: The internal study design is such that it sets out to do what it claims to do.

External Validity:
The capacity of a study to be generalisable to a target population outside sample studied.

Question 6

Criterion Validity
which is distinguished into
Concurrent Validity and
Predictive Validity

Answer 6

The extend to which the measurement correlates with an external criterion of the phenomenon under study. 2 Aspects of criterion validity can be distinguished:

• Concurrent Validity
• predictive validity

1. concurrent- measurement and criterion refer to same point in time. An ex would be an ankle jerk is missing and the person has a disc herniation at L5/S1.
2. Predictive Validity:
   - Measurments validity is expressed in terms of its ability to predict the criterion.

Question 7

Measurement validity?

Answer 7

Degree to which a measurement measures what its supposed to measure
eg Let us assume that SLR was proven to be a reliable measure such that it had excellent inter and intra rater reliability. This does not necessarily mean that it is a valid measure of disc herniation.

Question 8

Whats construct validity?

Answer 8

The extent to which the measurement corresponds to theoretical concepts concerning the phenomenon under study. e.g. spinal degeneration wrens with each decade, history of labouring and family history of degeneration

Question 9

Whats content Validity?

Answer 9

The extend to which the measurement incorporates the domain of phenomenon under study. Ie the content of the measure has to make sense.
eg a measurement of pain levels should include a reliable scale of measuring pain

Question 10

What is Face Validity?

Answer 10

You read about a new instrument (survey style measure) designed to measure neck disability and after pursuing the questions you decide that it appears valid (on the face of it)