RM- Reliability Flashcards
How can we assess reliability of observations using TEST RETEST method?
Repeat observation a second time by using the same participants and compare results gained from second observation, with the results gained from the first observation. The results should be very similar and produce a correlation coefficient of +0.8 or more in order to be reliable.
How can we assess reliability of observations using INTER RATER RELIABILITY method?
Use more than one observer/psychologist to observe and record the behaviours separately. The results from both psychologists could be compared and should gain a positive correlation of +0.8 or more if observation is reliable.
How can we assess reliability of observations using PILOT STUDY method?
Conduct a small trial run of the observation, before the main research study is carried out. Includes standardised instructions, debriefing and planning procedures properly to minimise human error.
- All key concepts and terms are operationalised.
How can we assess reliability of self reports using TEST RETEST method?
Give a self-report to a group of participants and collect the results. Give the same participants the same self report to complete a second time and compare results from 1st self-report to 2nd self report. Results should be similar with a correlation coefficient of +0.8 or more to be reliable.
How can we assess reliability of self reports using INTER RATER RELIABILITY method?
- If conducting an interview use more than one psychologist to interview pps and record seperately.
- Researchers need to act in similar and consistent ways.
- The results from both psychologists could be compared and should gain a positive coefficient of +0.8 or more if the interview is reliable.
How can we assess reliability of experiments using TEST RETEST method?
Conduct the experiment once and collect the results. Repeat the experiment again a few weeks later with the same participants who will be tested in exactly the same way. Compare results gained from both occasions and if reliable should have a correlation coefficient of +0.8 or more.
How can we improve reliability of experiments?
Via standardisation of instructions: Procedures should be exactly the same for each participant that takes part in experiment. Key concepts and variables should be operationalised.
How can we improve reliability of interviews ?
- Interview questions are not too leading/ ambiguous, they should be very clear so pps can understand them.
- easier to avoid leading questions in structured interviews
How can we improve reliability of observations?
- If inter observer reliability is low, make sure behavioural categories have been operationalised properly and clearly so observer understands categories properly when observing data,
- If results from pilot study not very clear then give more training and practice to observers.
What is reliability?
Reliability refers to the consistency of a research study especially when a study is repeated again and same results are gained on both occasions.
What is internal reliability?
- This is whether a test and the results gained are consistent within itself.
What is used to assess internal reliability?
- Split half technique.
- Questionnaire is split in half and if pps score similarly on both halves of questionnaire then it has internal reliability.
What is external reliability?
- This is whether a test and the results are gained are consistent over time.
What is used to assess external reliability?
- Test-retest method
improving reliability for questionnaires :
- some items of the questionnaire need to be rewritten or deselected
- for example, ambitious questions can be interpreted differently, so less use of open ended questions
