Validity and reliability

Question 1

What is validity?

Answer 1

Whether a study actually measures what it claims to be measuring or a theory explains what it intends to explain

Question 2

What are the 2 main types of validity?

Answer 2

Internal validity and external validity

Question 3

What is internal validity?

Answer 3

This is a measure of how certain the researchers are that the effects observed in a study are due to the manipulation of the independent variable (IV) and not confounding (CVs) or extraneous variables (EVs)

Question 4

What are the 2 types of internal validity?

Answer 4

Face validity and concurrent validity

Question 5

What gives a research study high internal validity?

Answer 5

Direct manipulation of the IV and high levels of control over other variables will give
a research study high internal validity

Question 6

Why is high internal validity a strength?

Answer 6

It allows psychologists to draw conclusions about cause-and-effect relationships between variables and these conclusions can be used to develop theories about behaviour

Question 7

Why is low internal validity a weakness?

Answer 7

Low internal validity is a weakness because the data cannot be used to draw
conclusions about cause-and-effect relationships and so the research is less likely to
have a meaningful impact on our understanding

Question 8

What is face validity?

Answer 8

This is a superficial way of assessing internal validity – it considers to
what extent something ‘appears’ to measure what it intends to measure

Question 9

What is concurrent validity?

Answer 9

this method assesses whether a test measures what it intends
to measure by comparing the data it produces with the data produced by a previously
established test (using the same participants)

Question 10

What is high concurrent validity?

Answer 10

High concurrent validity is where there is close agreement in the two data sets, this is indicated by a correlation coefficient of +0.8 or higher

Question 11

What is external validity?

Answer 11

This is a measure of how representative the research or theory is and to
what extent it can be generalised

Question 12

What are the 3 types of external validity?

Answer 12

Ecological validity, temporal validity and population validity

Question 13

What is ecological validity?

Answer 13

This is the extent to which the behaviours that are observed
and recorded in a study reflect the behaviours that actually occur in the real world

Question 14

What is an example of something with low ecological validity?

Answer 14

A lab study has low ecological validity because behaviours are likely to be
influenced by the artificial nature of the experiment. The high levels of
control mean that the situation is not representative of ‘everyday’ situations
and scenarios.

Question 15

What is temporal validity?

Answer 15

This is the extent to which the behaviours that are observed and recorded in a study hold up over time

Question 16

What is an example of what temporal validity would be?

Answer 16

For example, if the study was carried out many years in the past, to what extent are the behaviours representative of behaviours seen in the present day?

Question 17

What is population validity?

Answer 17

This is the extent to which the behaviours that are observed and recorded in a study are representative of people beyond the sample population, to other genders, cultures and age demographics

Question 18

How can the internal validity of a study be improved?

Answer 18

• Controlling EVs
• Managing e.g. make changes to reduce demand characteristics, experimenter bias, include a ‘lie scale’, ensure anonymity
• Identifying problematic instructions/ questions (on questionnaires)/designs then making changes

Question 19

How can the external validity of a study be improved?

Answer 19

• Using a broader sample and/or larger sample size
• Improving the ‘realism’ of the study

Question 20

What is reliability?

Answer 20

Refers to how consistent something is. This might be how consistent a study is in producing the same results from the same sample, using the same standardised methods, or how consistent a theory is in explaining the same set of behaviours over time.

Question 21

What is internal reliability?

Answer 21

Assesses the consistency of results across items within a test

Question 22

What can be used to assess internal reliability?

Answer 22

• ‘Split-half’ method
• Inter-observe reliability

Question 23

What is the ‘split-half’ method?

Answer 23

Where the results from one half of the test are compared against the results from the other half. If both halves yield the same outcome, the internal reliability is high

Question 24

What is inter-observer reliability?

Answer 24

Two or more observers gather data from the same source, using the same methods. High levels of consistency (+0.8 correlation or higher) would indicate high internal reliability.

Question 25

What is external reliability?

Answer 25

Assesses the consistency of a procedure, it would have high external validity if it produces the same results over time or from one occasion to another.

Question 26

How can external reliability be tested?

Answer 26

Using the test-retest method. Consistency across the two sets of
data would indicate high external reliability.