Validity and Reliability

external reliability

The extent to which a measure varies from one use to another

test-retest reliability

 the same person is asked to undertake the research measure on different occasions.

 

Important to remember that the participants are being studied twice, so the researchers need to be aware of any potential demand characteristics (they could be testing memory rather than reliability)

 

In addition if there is too much time between tests it could be possible that what they are measuring in participants will genuinely change.

inter-observer/rater reliability

The extent to which two or more observers are observing and recording behaviour consistently. This is useful in situations where there may be subjectivity.

 

When behavioural categories are being applies inter-observer reliability is important to make sure the categories are being used correctly.

 how the reliability of questionnaires can be improved

It will be possible to identify which questions are having the biggest impact upon reliability adjust them as necessary. This can be solved by re-writing them in a manner that reduces the potential for them to be incorrectly interpreted to reduce ambiguity.

 how the reliability of interviews can be improved

Ensuring that the same interviewer is conducting all interviews will help reduce researcher bias- differences in the way a question is asked can lead to different responses

 

Some researchers may ask questions which are open to interpretation- if the same interviewer cannot be used that training should be provided in order to limit bias.

 

The interview should be structured.

 how the reliability of observations can be improved

Observations can lack objectivity since they are relying on the researcher's interpretations of a situation.

 

If behavioural categories are being used, it is important that the researcher is applying them accurately and not being subjective.

 

This can be helped by operationalising categories- leaving no room for personal interpretation.

 internal validity

Whether a test really measures what it claims to measure i.e. is it accurate?

Lab experiments are higher in internal validity

 external validity

A measure of whether data can be generalised to other situations outside of the research environment.

 ecological validity

A type of external validity, refers to the extent to which psychologists can apply their findings to other settings- predominantly to everyday life.

temporal validity

A type of external validity which refers to the extent to which research findings can be applied across time.- an example in Asch's Study as it occurred in a more conformist era and the results are not applicable to today's society.

face validity

Whether items on a questionnaire look like what they are really measuring what it claims to measure

 concurrent validity

Comparing scores in this test to the scores on a well-established test.

Population validity

If the results can be applied to the target population.

 how the validity of experiments can be improved

Control groups: uses in experimental research to allow psychologists to see whether the IV is what is affecting the DV

Single-blind: means that participants do not know what condition they are in

double-blind procedures: neither the participant nor the researcher knows what condition they are in. this prevents demand characteristics or investigator effects.

Standardisation: minimises investigator effects and reduces possibility for different interpretations.

validity of questionnaires can be improved

Lie scale check: checks the consistency of responses by having two items that ask the same thing but in opposite ways.

Anonymous promise: by remaining unidentifiable participants are less likely to give answers that are socially desirable

 how the validity of observations can be improved

Covert observation: where the researcher is not seen- this increases the likelihood that any behaviour observed is natural.

Behavioural categories: researchers will tick off behaviours when they are seen, this reduces researcher subjectivity. Improves validity.

Qualitive methodology: has higher ecological validity due to depth of data that is collected, often through the use of case studies or interviews. Validity can be lowered because analysisis is more subjective. Direct quotes and multiple sources should be used.

Triangulation: use of multiple sources (interviews, observations and written reports)