validity and reliability

Question 1

Define reliability

Answer 1

The extent to which a test produces consistent findings every time is done

Question 2

How can reliability be assessed

Answer 2

• test retest
• inter observer reliability

Question 3

Explain 2 methods of testing reliability

Answer 3

Test retest - compares results from the same study from two separate occasions, results are correlated and A correlation coefficient over 0.8 is seen as reliable

Inter rater reliability- When two observers carry out the same observation separately and then correlate their results a correlation coefficient over 0.8 is seen as reliable

Question 4

How can reliability be improved

Answer 4

• Have highly trained observers or interviewer
• Clear standardised procedure
• Structured interviews and close question questionnaires
• use an established questionnaire or procedure

Question 5

Define validity

Answer 5

• Whether a measure actually measures what it claims to be measuring

Question 6

What are the two types of validity

Answer 6

• Internal validity (Are the results obtained solely affected by changes in the independent variable)
• External validity (Whether the data can be generalised to other situations outside of the research environment) 

Question 7

What factors influence internal validity

Answer 7

• Social desirability bias
  - Demand characteristics
• Investigator effects
• How’s standardised the procedure is

Question 8

How can internal validity be improved

Answer 8

• Single and double blinds prevent investigator effects and demand characteristics
• A clear standardised procedure controls variables
• Counterbalancing reduces order effects
• Random allocation
• Peer review 

Question 9

What are the types of external validity

Answer 9

Ecological validity- The extent to which findings can be generalised to other settings than the research setting
Mundane realism – the extent to which the tasks or activities are similar to what would be experienced in the real world
Population validity – the extent to which the sample is representative of the target population
Temporal validity – the extent to which findings can be generalised over time

Question 10

How can external validity be improved

Answer 10

• Replication of the study using different variations across time, different samples and different settings

Question 11

How can validity be assessed

Answer 11

• face validity- One or more judges assess whether the test or measuring tool appears to be appropriate
• Concurrent validity – compares a new measurement tool with a validated old one, Correlates the measurements from them both if the correlation coefficient is 0.8 or higher than the measuring tool is seen as valid