validity Flashcards
1
Q
types of validity
A
- refers to whether a test, observation, experiment etc. produces a result that is legitimate, or whether the result is genuine and represents what is actually real in the world
- includes whether the researcher has measured what they ended to measure (internal validity) and the extent to which findings can be generalised beyond the research setting (external validity)
- it is possible for studies and measures to produce reliable data that is not valid, for example, a broken set of scales may give a consistent of someones measure but always be 7lbs more then their actual weight
2
Q
types of validity - internal validity
A
- whether effects observed are due to manipulation of IV or some other factor
- one major threat to internal validity is iff participants respond to demand characteristics and act in a way that they think is expected
- for example, some have questioned internal validity of Milgram’s studies because participants may have just been laying along and ddi not really believe that they were administering shocks
3
Q
types of validity - external validity
A
- refers to factors outside of investigation, such as generalising to other settings or populations
- ecological validity is an example, concerns generalising findings from a study to another setting
- if the task that is used to measure the dependent variable is not like everyday life (low mundane realism), it has lower ecological validity
- must look at all aspects of research set up in order to decide whether findings can be generalised
4
Q
types of validity - temporal validity
A
- issue of whether findings from a particular study, or concepts within a theory, hold true over time
- it is suggested that high rates of conformity in original Asch study were a product of a particularly conformist era in the 1950s
- some of Freud’s concepts, like penis envy, are deemed to be outdated, sexist and a reflection of the patriarchal Victorian society within which he lived
5
Q
ways of assessing validity
A
- one form of validity is face validity, whether a test, scale or measure appears on the ‘face of it’ to measure what it is supposed to measure
- can be determined by eyeballing the measuring instrument or passing it to an expert to measure
- concurrent validity is demonstrated when results are very close to or match those obtained on another recognised and well-established test
- for example, a new IQ test may be used, and results may be compared with those from a well-established IQ test
- close agreement is indicated if correlation exceeds +.80
6
Q
improving validity - experiments
A
- can use a control group so that researcher can better assess whether changes in DV are due to effect of IV
- may also standardise procedures to minimise effect of participant reactivity and investigator effects
- single-blind and double-blind procedures also achieve the same thing
7
Q
improving validity - questionnaires
A
- many questionnaires and psychological tests involve a lie scale in order to assess consistency of responses and to control effects of social desirability bias
- also may assure respondents that responses will remain anonymous
8
Q
improving validity - observations
A
- may produce findings with high ecological validity as there may be minimal intervention from researcher
- especially in covert observations, behaviour is more likely to be natural and authentic
- behavioural categories that are too broad, overlapping or ambiguous may have a negative effect on validity of data collected
9
Q
improving validity - qualitative research
A
- usually have higher ecological validity due to the depth and detail associated with case studies, for example
- researcher may still have to demonstrate interpretive validity of conclusions
- extent to which researcher’s interpretation of events matches that of the participant
- validity further enhanced through triangulation, the use of a number of different sources for evidence
