is concerned with the consistancy of the test. it can be tested out by using the split hald method. this compares ine half of the other half by checking results of each half vary or are consistant.
1 of 23
external reliability
the ability to produce the same results every time that the research is done. it is assessed by using the test-retest method.
2 of 23
improving reliability
reliability depends on making accurate measurements so in order to improve reliability it is better to take more than one measurement from each RP. piolet studies can be used to improve this.
3 of 23
inter-rater reliability
where mroe than one investigator is used to collect data in the study. data should be standardized. investigators may need to be trained to make sure they are recording the same things.
4 of 23
validity
how well the rest or research actually measures what it says it will measure.
5 of 23
internal validity
this is the idea the study really does test what it is designed to test.
6 of 23
single-blind test
helps to reduce demand characteristics of RPs as they dont know what control group they are in. therefore do not know how to alter their behavior.
7 of 23
double-blind test
both demand characteristics and experimeter effects are not there are the researcher and RPs do not know what condition the RPs are in.
8 of 23
Face validity
the judgement about whether a test seems to measure what it claims to measure. this is the weakest way to measure validity.
9 of 23
concurrent validity
a test shows concurrent validity if it agrees with the findings of an existing test that measured the same thing.
10 of 23
predictive validity
measure of how well the test predicts future performances.
11 of 23
deception (presumptive consent)
must not lie to or decieve the RPs.
12 of 23
informed consent (prior general consent)
what we are going to do and why.
13 of 23
protection of participants (parental consent)
protect RPs from physical or mental harm.
14 of 23
probability
is how likely something is to happen or not happen. it is expressed as a number between 0 and 1.
15 of 23
statistical significance
if the result of a study shows a pattern we need to know if that is meaningful or just a chance. it will look at the differnece between scores to know if they are great enough to say it has significiance or if they arent good enough which puts it dow
16 of 23
Type 1 error
when you accept the experimental hypothesis and reject the null hypothesis when you should have accepted the null. this is a result of the significance level being to lenient.
17 of 23
Type 2 error
when you accept the null hypothesis and reject the experimental hypothesis when you should have accepted the experimental hypothesis. This is a result o the significance level being to stringent.
18 of 23
Nominal data
this data is sorted and counted in groups or catagories.
19 of 23
ordinal data
this data is put into an order and its position is noted.
20 of 23
interpretive phenomenological analysis
this involves interpreting the meanings that particular events or experiences have for RPs.
21 of 23
grounded theory
this is coding each line of text. it is coded into a general area or theme and then can be studied or compared to other studies.
22 of 23
disocurse analysis
involves the analysis of speech or written discourse. it also looks at the social contect of the discourse and the interaction between speakers.
23 of 23
Other cards in this set
Card 2
Front
the ability to produce the same results every time that the research is done. it is assessed by using the test-retest method.
Back
external reliability
Card 3
Front
reliability depends on making accurate measurements so in order to improve reliability it is better to take more than one measurement from each RP. piolet studies can be used to improve this.
Back
Card 4
Front
where mroe than one investigator is used to collect data in the study. data should be standardized. investigators may need to be trained to make sure they are recording the same things.
Back
Card 5
Front
how well the rest or research actually measures what it says it will measure.
Comments
No comments have yet been made