research methods ; reliability

1 of 41
a measure of?
2 of 41
in general terms a measurement is reliable if what can happen to it?
it can be repeated
3 of 41
so basically what is the question here to do with rulers and friends?
can researchers have the same confidence in their psych tests / obs / questionnaires as most of us have in rulers
4 of 41
5 of 41
- test-retest
6 of 41
what do you do?
administering the same test / questionnaire to the same person on different occasions
7 of 41
what will happen if test is reliable
results should be the same or @ least similar
8 of 41
method most commonly applied to?
questionnaires / psych ests
9 of 41
why must there be sufficient time between test and retest?
ensure the pp can't recall answers to qs
10 of 41
but can;t be so long that?
opiinons / balilites have changed
11 of 41
in case of questionnaire / test what wuld happen to scores to make sure similar?
12 of 41
when is reliability of measuring instrument assumed to be good?
when correlation turns out to be significant
13 of 41
- inter-observer reliability
14 of 41
eye of the beholder relevant to observational research why?
one researcher may interpret things differet
15 of 41
what does this introduce to data collection process?
subjectivity / bias
16 of 41
what do they do to combat this?
have researchers conduct observations in @ least teams of two
17 of 41
howver what must b established?
inter-observer reliability
18 of 41
this may involve pilot study why?
check observers are applying behaviour categories same way
19 of 41
observers watch same event but record data?
20 of 41
what should happen after to assess reliability?
data should be correlated
21 of 41
22 of 41
- questionnaires
23 of 41
comparing two sets of data should proceed correlation that exceeds?
24 of 41
what should happen if q comes up with low test-retest?
some qs may need to be deselected / rewritten
25 of 41
one solution may be to replace some of the open questions with?
closed fixed choice alternatives which may be less ambiguous
26 of 41
- interviews
27 of 41
for interviews what is probs best way of ensuring reliability?
use same interviewer each time
28 of 41
if this isn't practical what should happen?
interviewers shold be properly trained
29 of 41
what kind of interviewers are easier to do this with?
structured interviews
30 of 41
what kind of interviews are less likely to be reliable?
unstructured 'free-flowing' ones
31 of 41
- experiments
32 of 41
why are lab experiments often described reliable?
rsrcher can exert strict ctrl over many aspects of the procedure e.g instructions pps recieve / condts
33 of 41
control is more achievable in lab but lab reliability is more about relication of method than?
reliability of a finding
34 of 41
but what is one bad thing about labs that can affect reliability of finding?
pps tested under slightly different condts each time tested
35 of 41
- observations
36 of 41
reliability of obersvations can be improved by?
making sure behavioural categories have been properly observationalised
37 of 41
and that they are?
measurable / self-evident
38 of 41
what should categories not do?
39 of 41
and what should be covered on checklist?
all possible behaviours
40 of 41
what happens if these things don't happen?
different observers have to make own judgement of what to record where and may have inconsistent records
41 of 41

Other cards in this set

Card 2


a measure of?



Card 3


in general terms a measurement is reliable if what can happen to it?


Preview of the front of card 3

Card 4


so basically what is the question here to do with rulers and friends?


Preview of the front of card 4

Card 5




Preview of the front of card 5
View more cards


No comments have yet been made

Similar Psychology resources:

See all Psychology resources »See all Research methods and techniques resources »