RELIABILITY AND VALIDITY Flashcards

1
Q

Define reliability

A
  • reliability is a measure of consistency.
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
2
Q

Test-retest reliability

A
  • test the same person twice
  • If test Is reliable the results should be the same or very similar
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
3
Q

inter observer relability

A
  • compares observations from diff oservers.
  • E.g two or more oservers compare data by conducting a pilot study.
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
4
Q

How Is reliability measured

A
  • the corrlation co-efficent should exceed +.80 for reliability.
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
5
Q

How can you improve reliabity questionares

A
  • re write questions
  • Replace open with closed questions.
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
6
Q

How to improve reliability of interviews

A
  • improved training
  • use the same interviewer.
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
7
Q

How to improve reliablity of observations

A
  • Operationalisation of behavioural categories
  • Categoties shouldnt overlap
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
8
Q

how to improve reliability of experiment

A
  • the procedure must be consisent standardised procedure.
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
9
Q

Define validity

A
  • is the result legitimate
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
10
Q

How can data be reliable but not valid

A
  • people are tested but not measured what it intends on measuring
  • e.g an IQ test produces the same results every time.
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
11
Q

internal validity

A
  • control within study reduces demand characteristics
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
12
Q

External validity

A

Generalised to other settIngs, areas etc

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
13
Q

Ecological validity

A
  • refers to the extent to which the findings can be generalized to a real-life setting.
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
14
Q

Temporal validity

A
  • findings should be consistent over time
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
15
Q

2 ways of accessing validity

A
  • concurrent validity
  • Face validity
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
16
Q

Face validity

A
  • way of assessing whether or not something measures what it claims to measure.
17
Q

Concurrent validity

A
  • comparing a new test with an existing test (of the same nature) to see if they produce similar results.
  • If both tests produce similar results, then the new test concurrent validity.
18
Q

How can we improve validity of experiments

A
  • a control group means able to identify changes of dv were due to the effect of iv
19
Q

Improve validity of questionnaires

A
  • a lie scale and confidentiality
20
Q

How to improve validity of observations

A
  • good categories that are well defined
21
Q

How to improve validity of qualitative research.

A
  • interpretive validity shown through the coherence of narrative and direct quotes from pp
22
Q

Double bind

A
  • where neither research or pp know who’s reciving treatment
  • prevents bias