Reliability across all methods of investigation.

Question 1

What is reliability?

Answer 1

Consistency - how consistent a measuring device is. A research method is considered reliable if we can repeat it and get the same results.

Question 2

What are the ways of assessing reliability?

Answer 2

1. Test-retest
2. Inter-observer reliability

Question 3

Explain test-retest

Answer 3

• Carry out the test first time
• Carry it out again on the same people at a later date (i.e. re test)
• Correlate to check that they are similar
• Reliability = correlation of +0.8 or more

Question 4

Explain inter-observer reliability

Answer 4

• Have a second researcher to carry out the research too
• They both observe the same thing but do it separately
• Correlate their results looking for a +0.8 correlation

Question 5

How to improve reliability of questionnaires

Answer 5

remove some questions, rewrite some e.g. if they are ambiguous. Could replace some open questions with closed to reduce ambiguity

Question 6

How to improve reliability of interviews

Answer 6

use same interviewer each time if possible. If not, train all interviewers to avoid things like leading questions. Could use structured to have more control over the questions.

Question 7

How to improve reliability of experiments

Answer 7

use a lab experiment so it has control and is consistent so allows method to be replicable. Make sure it is standardised.

Question 8

How to improve reliability of observations

Answer 8

make sure behavioural categories are operationalised i.e. measurable and self-evident. Make sure they don’t overlap and all behaviours are covered on the list. Train observers too.