improving reliability

Question 1

what are the two methods of improving reliability

Answer 1

-the split-half method
-the test-retest

Question 2

how does the split- half method work

Answer 2

-randomly choose half the questions on the test and compare the results with the other half
-if significant +ve correlation between two halves then questions are reliable

Question 3

strength of using the split-half method

Answer 3

-don’t have to wait for the participant to forge the questions between the two halves of the test
-quick and easy way to establish reliability

Question 4

weakness of using the split-half method

Answer 4

-only effective with large questionnaires
-in which all questions measure the behaviour being researched

Question 5

how would u use the split-half method of assessing reliability to improve reliability of tests

Answer 5

-unreliable questions are removed until reliability is established

Question 6

what does the test-retest method involve

Answer 6

-administering an entire test to a participant
-waiting for them to forget the questions (could take several months)
-readministering the test

Question 7

what do the results from a test-retest indicate

Answer 7

-if the results from both presentations of the test significantly positively correlate then its a reliable test

Question 8

strength of test-retest

Answer 8

-every question is checked for reliability so unreliable ones removed

Question 9

weakness for test-retest method of assessing reliability

Answer 9

-takes a long time for results to be obtained
-if too long an interval has been used the participant may have changed in themselves meaning it is wrongly declared unreliable

Question 10

how would you use test-retest to improve reliability of a test

Answer 10

-unreliable questions removed until reliability is established

Question 11

how to assess reliability of experiments

Answer 11

-dependent variable measured using a rating scale
-e.g. bandura (bobo doll)
-method used to measure the DV is consistent (e.g. observations)

Question 12

how to improve reliability of experiments

Answer 12

standardisation
-procedures must be exactly the same for different ppts or on different occasions

Question 13

how to improve the reliability of questionnaires

Answer 13

-over time they should be measured using test-retest and compare the two data sets
-correlation coefficient needs to be +0.8 to be reliable
-if low test-retest reliability some items need to be rewritten to reduce ambiguousness of interpretation

Question 14

how to improve reliability of interviews

Answer 14

-use the same interviewer each time
-each interviewer has to be trained in order to avoid asking leading/ambiguous questions
-more easily done in structured interviews due to fixed questions whereas unstructured are les likely to be reliable

Question 15

how would you improve the reliability of observations

Answer 15

-operationalising behavioural categories
-make sure they are measurable and self-evident
-categories shouldn’t overlap to remove uncertainty and produce inconsistent results
-if low, observers need further training in using behavioural categories

Question 16

how can you improve the reliability of experiments

Answer 16

-lab more reliable due to control over variables due to standardised procedures
-one factor affecting reliability of experiments is if the pps are tested under even slightly different conditions

Question 17

how to use reliability as an evaluation

Answer 17

-internal and external reliability

Question 18

how would u asses internal reliability with a questionnaire and observation

Answer 18

questionnaire- mention split half as a way of assessing reliability
observation- mention having two or more observers and checking for inter observer reliability

Question 19

how would u assess external reliability with a questionnaire and experiment

Answer 19

questionnaire- mention test-retest as a way of assessing reliability
experiment- mention whether replication is possible (standardisation) or actually replication to check for reliability or is it already a replication?

Question 20

why is it important for research to be replicated

Answer 20

-likelihood of the same differences occurring twice (or more), by chance
alone are much smaller than when they occur the first time.
* Effects that occur in a study are more likely to be reliable if they occur in a
repeat of the study – replication therefore increases (external) reliabilit