what is reliability
-when a measurement tool is used and gets the same results every time
-whether something is consistent
what result should the tool produce if measuring the same thing
the same result on every occasion
if the results of the same test is different, what must we ensure
that its the thing we are testing that’s changed not our tool
if the exact same results are difficult to obtain, what does psychology use instead
-a strong positive correlation
what do you need in order to assess reliability
-an observational research study using more than one observer
when is data unreliable between observers
if different observers provide significantly different observations of the same behaviour
how can observer reliability be assessed
-by correlating the data provided by the observers
-High correlation = high agreement = reliable test
how to improve the reliability of observers
-train observers in techniques being used
-make sure everyone agrees with them
what can you do to improve the reliability of categories
-ensure they are correctly and objectively operationalised
-means behaviour being observed can ONLY be that behaviour
what is reliability mainly referred to in psychology
-observations
how to conduct inter-rater reliability (INTER acryonym)
I- involve a third observer
N- name categories you will use
T- tally behaviours observed separately
E- establish if there’s a correlation
R- reliability is +0.8 or more