Methodological Issues Flashcards
Representative
When the sample reflects the population
Reliability
Consistency of results
Whether a test can be used more than once to produce consistent results
Internal reliability
Consistency of results of a test across items within that test (first half of test give similar results as second half)
Split half method
Testing one half of the questions to get a score and then testing the other half of questions to see if the same score was achieved (every other question, first half of questions, first third and quarter)
Internal validity
The extent to which the findings are measuring what they intended to measure
External reliability
The extent to which test scores varies from one time to another
Test-re test method
Used to see if the same results are achieved
Inter-rater reliability
2 observers rate or observe the same behaviours and the 2 sets are correlated
If a significant positive correlation is seen, inter rater reliability has been established
Validity
How accurate a test is at measuring what it aims to measure
External validity
The extent to which the findings can be generalised outside the study
Face validity
How good the research is at testing what it is meant to test (measuring circumference of someone’s head to measure intelligence)
Construct validity
Whether the test measures the actual behaviour it sets out to measure (test of general knowledge to test intelligence, this is a bad way)
Concurrent validity
Where the test or research gives the same results as another test or study which is meant to measure the same behaviour (Loftus and Palmer)
Criterion validity
How much one measure predicts the value of another measure
Predictive validity
Where the test predicts certain behaviours (a levels to predict success at uni)
Population validity
The extent to which the findings can be generalised to other people
Ecological validity
The extent to which the findings can be generalised to other places/real life
Demand characteristics
Clues which alert participants to the true aims of the study
Social desirability bias
Trying to look good
Making yourself look socially acceptable
Researcher/observer effects
Participants being influenced by researchers presence (Ofsted)
Gender/age may influence results in interviews
Researcher bias
Researcher shows bias when collecting the data
Reduced by not knowing what condition ppts were in
Researcher may try to support hypothesis so act bias
Ethical considerations
Informed consent Right to withdraw Confidentiality Protection of participants Debrief Deception
Generalisability
The ability to generalise the results to the general population
