Reliability and Validity

Question 1

What is reliability?

Answer 1

It refers to the consistency i.e the ability to get the same results. If the study is repeated under the same method, design and measurements and the same results are obtained that results are said to be reliable

Question 2

What are the two types of reliability?

Answer 2

Internal and external

Question 3

What is internal reliability?

Answer 3

The extent to which the measures used within an investigation are consistent e.g. making sure that anything used within the study is the same

Question 4

What is external reliability?

Answer 4

The extent to which a test gets the same results over time, each time the test is repeated e.g the results of the study are the same

Question 5

How do you assess internal reliability?

Answer 5

By using the split half method. This is splitting the test into two (e.g odd and even questions) and having the same participants complete both halves. If the two halves of the test provide a similar scores, this indicates that the test itself has internal reliability

Question 6

How do you assess external reliability?

Answer 6

The test retest method. This involves giving the same test to the same participants on two different occasions and if the same results are obtained then the external reliability is established

Question 7

What is inter observer reliability?

Answer 7

It is used for observations and sometimes interviews. It’s a means of assessing whether different observers are viewing and rating behaviour in the same way. This can be achieved by conducting a correlation of the observers scores. A high positive correlation would indicate that they are categorising behaviour consistently

Question 8

How can inter observer reliability be improved?

Answer 8

Developing clearly defined and separate categories of observational criteria e.g instead of aggression you are looking for things like kicking, hitting and punching etc

Question 9

What are four ways of improving reliability?

Answer 9

1. Take more than one measurement for each participant and take an average score as it reduces the impact of any anomalous scores
2. Use clearly defined operational definitions for variables and behavioural categories
3. Pilot studies to check the proposed method of measurement works properly
4. When more than one investigator is used, the way in which they collect the data should be standardised, which may require training. This improves inter rather reliability

Question 10

What is validity?

Answer 10

It concerns accuracy and the degree to which something measures what it intends to. If refers to how accurately a study investigates what is claims to. It also concerns whether the findings are accurate beyond lab research and if they can be generalised

Question 11

What are the two types of validity?

Answer 11

Internal and external

Question 12

What is internal validity?

Answer 12

It concerns whether the results are due to manipulation of the IV and have not been affected by other confounding variables. If there are any extraneous variables you do not have internal validity

Question 13

What experimental method has the highest internal validity?

Answer 13

Lab experiment

Question 14

What is external validity?

Answer 14

Whether results can be generalised and are accurate in other settings (ecological validity), other people (population validity) and other time (temporal validity)

Question 15

What are the three ways of assessing internal validity?

Answer 15

Face validity, concurrent validity and predictive validity

Question 16

What is face validity?

Answer 16

The extent to which a measure at face value looks like it is measuring what it intends to. E.g a test on IQ which only requires participants to memories items is not a valid measure of IQ

Question 17

What is concurrent validity?

Answer 17

Correlating scores on a new test of unknown validity with another existing test that is known to be valid and trusted. If both questionnaires give similar results it is likely this new questionnaire has high validity

Question 18

What is predictive validity for assessing internal validity?

Answer 18

This refers to how well a test predicts future performance. E.g is a SATs test is given at age 7 and predicts the final grades achieved at GCSE, it would suggest the original test did actually measure academic ability and therefore establishes internal validity

Question 19

What are the two ways of assessing external validity?

Answer 19

Predictive ability and meta analysis

Question 20

What is predictive ability for assessing external validity?

Answer 20

As the researcher is measuring academic ability at two different points in time, if similar results are gained the second time round, it would also indicate temporal validity as the original results can be generalised to other time periods

Question 21

What is meta analysis for assessing external validity?

Answer 21

The comparison of findings from many studies that have investigated the same hypothesis. The studies are often carried out in different time periods, in different countries. If the findings are consistent across populations, locations and period in time then the meta analysis indicate external validity

Question 22

What are the four ways of improving internal validity?

Answer 22

1. Choose the appropriate experimental design
2. Control extraneous variables
3. Single blind technique
4. Double blind technique

Question 23

What are the two ways of improving external validity?

Answer 23

1. Sampling- use a method that enable the investigator to collect a representative sample
2. Realism- conduct it in a more realistic setting ensuring that the lab is as true to life as possible