Research methods 2

• How do you answer the following question in an exam?

  Explain why it would be appropriate for the researcher to use the 5% significance level in the investigation?

  1) Achieves balance between making a Type 1 error and a Type 2 error

  2) In this investigation a type 1 error would be saying ........

  3) In this investigation a type 2 error would be saying ..............
• In what ways does psychology affect the economy?


  Government, NHS, workplace and indivudual
• Why are the paradigm and paradigm shift important?


  When theories are disproved enough this lead to to a paradigm shift which enables science to progress through the process of scientific enquiry.
• Why is falsifiability important?


  In studies we try to prove hypothesis wrong and this means that falsifiability affects hypothesis that we test empirically and use to refine theories.
• Why is replicability so important?

  Science involves testing a hypothesis using empirical methods. Findings and conclusions from these studies are then used to construct theories so procedures need to be repeatable.
• Why are empirical methods important?


  Without these methods theories cannot be considered scientific and so less theory construction would be used. This affects hypothesis testing and may cause results to be objective.
• Why is hypothesis testing important?

  A hypothesis can be tested using empirical methods and if scientists fail to find data to support a theory then they know the theory requires construction.
• Why is theory construction important?

  Enables predictions to be made which can be translated to hypothesis and tested empirically
• Why is objectivity important?

  Without objectivity researcher can interpret variables differently as they are not operationalised. Therefore extraneous variables may affect the study and researcher may show unconscious bias
• Define paradigm and paradigm shift

  Paradigm = the basic assumption, ways of thinking and methods of study commonly accepted by members or a discipline or group

  Paradigm shift = When these ways of thinking and methods of studying change

  For example- psychologist used to thought observing behaviour was best but now it is recognised that understanding thought process is also important
• Define falsifiability


  Is the ability to prove a theory or construct wrong.
• Define replicability


  This means the study should produce the same results if repeated.
• Define empirical method


  This method uses objective, quantitative observations in a systematically controlled and replicable situation, in order to test or refine a theory
• Define hypothesis testing


  When research is undertaken to check whether a prediction is correct or not. If it is incorrect a theory will need to be changed.
• Define theory constructions

  It is normally devised from research guided by a testable hypothesis.
• Define scientific

  A study/theory is this if its replicable, objective, falsifiable, uses an empirical method.
• Define objectivity


  Something that is not affected by feelings/experiences of other researchers
• How can we improve the reliability of observations?


  - Operationalised behavioural categories (measurable and self-evident)

  - Categories shouldn't overlap and all behaviours should be covered on the check list
• How can we improve the reliability of experiments?

  - Standardised instructions/procedure

  - Often thought as very reliable as they occur in a lab so the experiment can be repeated to check for reliability
• How can we improve the reliability of interviews?


  - Use the same interviewer each time or ensure that the interviewers are all trained

  - Use structured interviews

  - Unstructured interviews = unreliable
• How can we improve the reliability of questionnaires?

  If test-retest is low some questions may be deleted or re-written e.g. an open question is changed to a closed question
• How would you assess the reliability of interviews?

  inter-rater reliability
• How would you assess the reliability of a content analysis?

  Inter-rater reliability
• How do we check for inter-observer reliability?

  1) 2+ observers choose behavioural categories

  2) 2+ observers watch the event separately and record data independently

  3) Data collected is correlated using an appropriate statistical test and should have correlation of 0.8 indicating good reliability
• What type of research is inter-observer reliability used to assess?

  Observational research
• Why do we need to be careful when using test-retest to check reliability?

  Must be sufficient amount of time between test and retest to ensure that participants cannot remember the first test. Additionally their needs to be not enough time where opinions may have changed
• How we use test-retest to ensure that it's reliable?


  The results to the test should be the same or very similar. Two sets of scores are correlated using a statistical test and should have a correlation of (+0.8)
• How can we do test-retest reliability?

  Involves administering the same test to the same person on different occasions
• What experimental method is test-retest reliability used for?

  Questionnaires and psychological tests
• What are the two ways of accessing reliability?

  - Test retest reliability

  - Inter observer reliability
• How can a measuring device by reliable?

  If it produces consistent results every time it's used
• Define reliability?

  A measure of consistency. It refers to how consistent the findings from an investigation or measuring device are.
• How can validity be improved in observations.


  - Use covert observations = minimal intervention by the researcher meaning high ecological validity

  - Use specific non-overlapping unambiguous behavioural categories
• How can validity be improved in questionnaires?

  - Use a lie scale = assess consistency of participants responses and controls for social desirability bias

  - Assure the participants their responses will remain anonymous = reduces the effect of social desirability bias
• How can validity be improved in Experimental research?

  - Use control groups = researcher can better assess if the change in behaviour is due to the IV or not

  - Use standardised instructions and procedures = this minimises investigator bias

  - Use single/double blind trials = minimises impact of investigator bias and also reduces the chances of demand characteristics
• What is concurrent validity?

  - Demonstrated when the results are the same or very close to another well-established test that measures the same concept.

  - This is tested by doing a correlation between scores that participants receive on both tests. If the correlation is strong and positive it is considered to be a valid test.
• What is face validity?


  - Whether the test, scale or measure appears to measure what it was suppose to on the face of it.

  - This is done by eyeballing it
• What are two ways to check validity?

  - Face validity

  - Concurrent validty
• Define ecological validity

  Whether the results of a study can be generalised beyond the particular setting in which it is demonstrated to other settings.
• Define external validity

  Whether the results can be generalised from research participants to people, places, and times outside the study.