Credibility is a term which can be used to evaluate quantitative and qualitative research. When applied to quantitative research it usually seen as something of an umbrella term and relates to the extent to which people should be feel that the results are trustworthy, i.e. it is about believability! Now this is of course an interesting concept because the extent to which a set of findings is believable is shaped by two things:
- qualities relating to the set of findings (objective credibility)
- qualities relating to the person doing the believing or disbelieving (subjective credibility)
If the person comes from a Western background and has been enculturated to believe in ‘the power of science’, then they are likely to judge a piece of research according to the extent to which they perceive it to be ‘scientific’. People who do not have a good knowledge of science but do know that science is valued may simply accept so-called ‘scientific’ research at face value and not think critically about the study.
People who know a bit more about science, such as member of the scientific community agree on a set of key characteristics that one would expect if a piece of work is to be called scientific and thus is believable/credible, e.g. the study will be
- internally valid: could the data have been affected by participant reactivity, researcher bias, operationalisation, control over extraneous variables, design related issues i.e. participant variables and order effects
- externally valid: (the extent to which the behaviour is an artifact of the experimental situation (lacking EV), on the one hand, or relates to natural behaviours that arise in everyday situations outside of the highly controlled laboratory setting (high EV).
- reliability: extent to which the findings are consistent across other similar studies (external reliability)
- replicable: extent to which the study lends itself to being carried out in exactly the same way by other researchers, in order to test reliability.