Research Methods: Reliability and Validity Flashcards

You may prefer our related Brainscape-certified flashcards:
1
Q

What is meant by the term validity?

It refers to whether …

A

the consistency of a study or a measuring device within a study

a study produces similar results if replicated

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

Name the 2 ways of assessing reliability

A

test-retest
inter-rater

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

Describe how test-retest is used to assess reliability

3 points

A

-the same study/analysis is carried out by same researcher twice times under the same conditions at different times

-results of the 2 analyses are compared and a correlation coefficient is calculated

-a correlation coefficient of + 0.80 indicates high reliabiltiy

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

Describe how inter-rater is used to assess reliability

A

-more than one researcher independently carries out the observation/analysis

-follow the same procedure regarding comparison and calculation of correlation coefficient

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

Give 3 ways the reliability of an experiment can be improved

A

-conduct lab experiments that follow standardised procedures
-operationalise variables
-use a pilot study to help identify any problems beforehand

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

Give 2 points about how the reliability of a questionaire can be improved

A

-use more closed questions
-deselect or rewrite questions is they are too complex or ambiguous

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

Give 3 ways the reliability of an interview can be improved

A

-use the same interviewer each time

-train interviewers to ensure they ask questions in the same way

-used structured interviews/scripted

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

Give 3 ways in which the reliability of an observation can be improved

A

-operationalise behavioural categories and discuss with other researchers so all are clear on how to interpret behaviour

-record data so it can be reviewed

-train observers

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

Validity concerns whether …

A

a test/measure/findings actually measure what they were intended to / claimed to measure

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

What is meant by internal validity

A

concerns the ability of a study to test the hypothesis it was designed to test

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

What is meant by external validity

A

concerns whether the findings of the study can be generalised beyond the study itself

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

What are the 3 main types of external validity ?

A

ecological validity
temporal validity
population validity

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

What is ecological validity?

A

the degree to which findings of a study can be generalised to other situations or are reflective of how a behaviour would occur under normal circumstances

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

What is temporal validity?

A

where research findings that took place at a certain time accurately reflect the way behaviour would occur at a different point in time

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

What is population validity?

A

where research findings can be generalised from the sample to other populations

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

Name the 2 ways of assessing validity

A

Face validity
Concurrent validity

17
Q

Describe what is meant by face validity

A

where a behaviour appears on face value to represent what is being measured

18
Q

Describe what is meant by concurrent validity

How is close agreement and therefore validity indicated ?

A

where performance on one measure highly correlates with performance on another established measure of the same variable

if the correlation between the 2 data sets is + 0.80