Reliability and Validity

The flashcards below were created by user camturnbull on FreezingBlue Flashcards.

  1. How can a study be said to be reliable?
    If the study was repeated the same results would be observed
  2. How can a study be said to be valid?
    If it successfully tests what the researchers intended to test
  3. What is reliability?
    The degree to which an instrument measures the same way each time it is used under the same conditions with the same participants
  4. What is external reliability?
    The consistency of measurements over time and situations
  5. What is internal reliability?
    The consistency within the measuring tool
  6. What is the test/retest method?
    • The process of testing the same group of participants on more than one occasion with the same test 
    • If it is reliable you should get the same results for both tests
  7. What is inter-observer reliability?
    • In observational research, two separate observers rate or code the different types of behaviour at the same time 
    • The observers work independently and compare recordings at the end of the observation 
    • If there is a strong positive correlation it can be said that there is good inter-observer reliability
  8. How can a test be reliable yet not valid?
    The same results can be collected again and again but they might not be what the researchers are trying to measure
  9. What is validity?
    Whether or not something measures what it intends to measure
  10. What is External Validity?
    • Our ability to generalise the results of our results to real life settings and other populations 
    • An example is ecological validity
  11. What is internal validity?
    Whether or not there is a relationship between the study and the observed outcome (Is it a causal relationship?).
  12. What is face validity?
    • A method of checking for internal validity 
    • Whether or not the test 'looks like' it is going to measure what it is supposed to measure
  13. What is concurrent validity?
    • A method of checking for internal validity
    • A new measurement is compared with a previous, already validated measurement 
    • If there is a positive correlation, the study can be said to have concurrent validity
  14. How might a study be said to be fatally flawed?
    If the results are neither reliable, nor valid
Card Set:
Reliability and Validity
2014-04-18 00:20:11
Psychology Methodology Reliability Validity camturnbull

AQA PSYB4 Research methods
Show Answers: