Validity Flashcards
Define the term validity.
Refers to whether the psychological study truly measured what it intended to measure, and whether the results can be generalised beyond research setting. It is possible to be reliable but not valid. However, it’s not possible to be unreliable but valid, as if the study is producing different results each time then this suggests there is something wrong with the method being used. There are many different types of validity.
Define the term internal validity.
Refers to whether the effects observed in an experiment are due to the manipulation of the independent variable and not some other factor.
One major threat to the internal validity of a student is if participants respond to demand characteristics.
Give an example of a threat to internal validity.
For example, some commentator have question internal validity of Milgram’s obedience study claiming that participants were ‘playing along’ with the experimental situation and didn’t believe they were administering shocks.
Define the term external validity.
This refers to whether the findings of a study really can be generalised beyond the study. We can break external validity down into three types:
Population validity.
Ecological validity.
Temporal validity.
Define the term population validity.
The extent to which the findings can be generalised to other populations of people.
Define the term ecological validity.
The extent to which the findings can be generalised to other situations outside of the research study. Often this means considering whether the study represents behaviour in a more natural setting.
Define temporal validity.
The extent to which the findings can be generalised to other time periods.
How can you assess validity?
One way of assessing validity is to use face validity which simply means looking at the test or questionnaire and deciding, at face value, if it measures what it intends to measure.
Concurrent validity can also be used. This is where the results of a test are compared with another existing, well-established test which measures the same thing, such as an IQ test for intelligence. If there is a strong positive correlation (above +0.8) between the participant’s scores on the two tests, then the test is likely to be valid.
How can you improve the validity of experiments?
Using a control group to compare the results of the experimental group - researcher better ability to assess whether changes in the dependent variable is due to the effect of the independent variable.
Standardise procedures to minimise impact of participant reactivity and investigator effects on the validity of the outcome.
Use of single and double blind procedures.
Give an example of control groups improving validity.
In a study looking at the effectiveness of a therapy, a control group who didn’t receive therapy means that the researcher can have greater confidence that improvement was due to effects of therapy rather than the passage of time.
How can you improve the validity of observation?
Covert observations are likely to be high in ecological validity. As the participant is unaware they are being observed, their behaviour is more likely to be natural. Having clear and unambiguous behavioural categories will also improve validity.
How can you improve the validity of questionnaires?
Keeping results anonymous increases the chances that the participant will answer truthfully.
A lie scale built in, which is a set of questions designed to test the truthfulness of a participant’s answers.
How can you improve the validity of qualitative methods?
Case studies and interviews (particularly unstructured ones) are thought to have higher ecological validity, as they more accurately reflect the richness and complexity of the human experience. The researcher must take care to clearly report any findings so that they are free from bias. Including direct quotes is an example of how this can be done. Triangulation is another way of enhancing validity for these methods.
Define the term triangulation.
Using a number of sources of evidence such as observations, interviews with family members, and so on.
