Reliability & Validity

If results are reliable they are

• Consistent

• Valid

• Correct

This involves testing the same group of participants on more than one occasion using the same test usually within a relatively short period of time. 

• Test re test

• Inter rater reliablity

• Concurrent validity

• Face Validity

After doing test re test to check for reliability the researcher needs to compare data from both tests. They are reliable if....

• Negative correlation -0.8 or above

• Positive correlation 0.8 or above

• Positive correlation 0.3 to 0.5

• Zero correlation

 2 or more researchers do an observation (independently) of the same thing but without talking to each other and then compare results via a stats test

• Test re test

• Inter observer reliability

• Concurrent validity

• Face Validity

Reorder the following for inter rater/observer reliability

• Need a correlation co-efficient of 0.8 or above to show reliable

• Compare the 2 sets of data via inferential stats test

• Devise behavioural categories, pilot them to make sure they are distinct and don't overlap

• 2 or more do observation independently of each other

The extent the study/method is actually measuring what it is claiming to measure is connected with which of the following?

• Consistent

• Valid

• Correct

Match the following

• External validity

• Refers to the extent to which the results of a study can be generalized to other settings other people and over time

• Temporal Validity

•  Refers to how well the results relate to contemporary times

• Internal validity

• Refers to how certain we are that we can generalise from the results to other people

• Ecological validity

•  Refers to how well the setting of the study relates to the real world. 

• Population Validity

• How certain can we be that the IV has caused the effect on the DV?

Asking other psychologists whether they think the test appears to measure the target variable. 

• Test re test

• Inter rater reliablity

• Concurrent validity

• Face Validity

The extent to which test scores correlate with scores on another existing established test administered at the same time.  

• Test re test

• Inter rater reliablity

• Concurrent validity

• Face Validity

Reorder the following - Process involved in concurrent validity when doing a personality questionnaire

• Need a correlation co-efficient of 0.8 or above to show concurrent validity

• Devise new personality test and get participants to complete it

• Give participants an established test for measuring personality

• Compare results from both questionnaires using stats test