reliability

Question 1

what is reliability

Answer 1

it is a measure of consistency

In general terms, if a particular measurement can be repeated then that measurement is described as being reliable

e.g. a ruler should find the same measurement for a particular object (e.g. a plant) every time we would attribute the change to the object rather than the ruler

Question 2

how do you assess reliability

Answer 2

there are two ways to test reliability:

test - retest

inter-observer/inter - rater

Question 3

what is test - retest

Answer 3

this is giving the same test/ questionnaire to the same person (people) at a later date

there must be sufficient time between test and retest to ensure the participant cannot recall their original answers but not so long that their attitudes, opinions or ability changed

if the questionnaire is reliable then the results should be the same or very similar

The researcher would check to see if there is a positive correlation between the two sets of scores (+0.8 or above). If there is they would say their test is reliable

a researcher could hen use a Spearman’s rho or Pearson’s r statistical test to check that the two sets of scores significantly correlate with each other

if the questionnaire

Question 4

what is inter - observer

Answer 4

1. everyone has a unique way of seeing the world. This issue is particularly relevant to observational research ass it may introduce subjectivity and bias and therefore lead to low reliability
2. inter-observer reliability involves two researchers independently recording their results and then seeing if thy correlate with each other
3. in an observation, a pilot study of the observation can be used to check that observers are applying the behavioural categories in the same way
4. observers will then watch the same event but record their data independently
5. they can then check their results positively correlate to assess reliability
6. if the results are reliable there will be a positive correlation of a +0.8 or above, again this can be checked a Spearman’s rho or Pearson’s r statistical test
7. Inter-observer can be used with other research techniques such as a constant answer or interview, in this case it us called “inter-rater” reliability

Question 5

what is validity

Answer 5

the extent to which an observed effect is genuine does it measure what it was supposed to measure (internal), and can it be generalised beyond the research setting within which it was found (external)

Question 6

what is external validity

Answer 6

can the results of an investigation be generalised beyond the research setting within which it was found

Question 7

what internal validity

Answer 7

does a test/ investigation measure what it was supposed to measure

Question 8

what are the types of external validity

Answer 8

temporal

ecological

Population:

Question 9

what is temporal validity

Answer 9

temporal: the external to which finding from a research study can be generalised to other historical times and eras

Question 10

what is ecological validity

Answer 10

ecological: the extent to which findings from a research study can be generalised to other settings and situations
- not always about “natural” the environment is. If the task used to measure the DV in an experiment is not like everyday life (low mundane realism) this will lower ecological validity
e. g. giving people a list of words to remember to assess memory in a shopping mall as part of field experiment. The setting doesn’t make the findings any more realistic

Question 11

what is population validty

Answer 11

Population:

- the extent t which findings from a research study can be generalised to other people outside the sample