RESEARCH METHODS - Reliability
- Created by: EmilyEther
- Created on: 19-03-19 13:10
View mindmap
- Reliability
- Assessing reliability
- def: the consistency of measurements. We would expect any measurement to produce the same data if taken on successive occasions
- def: inter-observer rel: the extent to which there is agreement between 2 or more observers involved in observations of a behav
- def: test-retest rel: the same test or interview is given to the same PPs on 2 occasions to see if the same results are obtained
- correlational tests
- Self-report techniques
- test-retest
- questionnaire given once and then given again to them a second time
- must be a while between the questionnaires - they may remember answers
- correlation can only be determined in closed questions (yes / no)
- if interview, needs to be very structured
- test-retest
- Banduras
- Bobo doll - observing the behaviour of the children and seeing how aggressive behaviour was. The DV is often measured on a rating scale in these experiments.
- Different researchers may rate the behaviour differently = issue for reliability because may lack consistency (inter-rater reliability)
- Improving the reliability
- reducing ambiguity
- everything should be standardised
- write of the procedure etc must be clear enough that someone else should be able to copy it exactly
- questionnaires - clear questions, no leading qus, pilot study should pick up on this
- reducing ambiguity
- Observational techniques
- behavioural categories - may not have been operationalised clearly enough
- need to identify the categories and clearly describe what is what
- improving rel: clearly define categories
- even if they are clearly defined, they make been mistaken. they make need to practice using the categories (in the pilot studies)
- Assessing reliability
Comments
No comments have yet been made