Reliability and validity Flashcards
what is reliability?
The term ‘reliability’ means dependability or consistency. If the findings from psychological research are replicated, then they can be said to be reliable.
what is validity?
Validity is concerned with the extent to which something measures what it sets out to measure. (has the aim of the study been met)
name the two different ways to make sure the research has reliability and can be repeated?
By the use of audio taping or videotaping.
How can reliability be increased in observational studies?
More than one observer should be used.
they should be trained and understand what they are looking for and what categories to put the behaviors into. independent checks for reliably would be easier to do if the observation was videoed or audio taped.
what is inter-rater reliability?
It is a procedure that allows the researcher to measure the extent in which observers agree on scoring behaviors.
How is the data obtained from each observer/ scorer then made into reliable results?
the sets of data is obtained from the individual scorers and correlated. observer reliability is achieved if the correlations between scorers are positive.
what is the split half method?
the method is splitting up a questionnaire into two e.g. the odd and even numbered questions results to see if they are consistent to each other. if the results have a positive correlation the questionnaire and results are reliable.
what is the test-retest?
it is used to asses the stability of a test or questionnaire over time. the test is presented to participants more than once on different occasions over time. if the results from the test and retests are positively correlated the test/questionnaire is stable.
when using a test-retest when is the best time to give the participants the retest?
it can’t be a short time after or the participants may remember their answers and it can’t be too long after because the participants personality’s may change which will affect the results.
what is internal validity?
concerned with the extent to which we can be sure that research findings are due to manipulation of the independent variable and not to the action of some other unwanted variable, such as individual differences or the effects of practice.
• Internal validity is also compromised if no effect is found within research when in fact an effect actually exists.
what is external validity?
• External validity is concerned with the extent to which results can be generalized beyond that of the study
what is population validity?
the extent to which results from research can be generalized to other groups of people.
what is ecological validity?
the extent to which research findings can be generalized to situations outside the research setting.
• Note that laboratory experiments do not automatically lack ecological validity. Similarly, the fact that research is carried out in a natural setting does not guarantee ecological validity. This may or may not be achieved - it all depends on whether or not the results can be generalized.
what is face validity?
the simplest technique is concerned with assessing whether a measuring instrument looks correct in the eyes of independent experts, who may suggest improvements to the researcher. Because of its subjectivity, face validity usually takes place in the earliest phases of constructing a measuring instrument
what is content validity?
is superficially similar to face validity. Independent experts are asked to assess the validity of the measuring instrument concerned. This time, however, there is a detailed and systematic examination of all the component parts.
