research methos continued

HideShow resource information
View mindmap
  • Research Methods
    • Experimental designs
      • Individual groups
        • 2 different groups of people do one condition each, in which the IV is manipulated differently each time
        • no order effects, so results more valid than repeated measures. same materials can be used
        • individual differences can lower internal validity. very small sample but expensive
      • Repeated measures
        • same group of PP's  do each condition
        • cheaper as can use same equipment and pp's. Participant variables eliminated because same pp each time
        • order effects lower internal validity, can be avoided by counter balancing
      • Matched Pairs
        • matched on variables, then assigned separate conditions
        • individual differences are lowered, increasing validity
        • time consuming
    • key definitions
      • operationalization
        • defining key variables precisely so they can be measured, observed and quantified. totally subjects to the researcher to decided
      • Hypotheses
        • Directional
          • has a directional prediction
        • Non-directional
          • stating there will be a difference but no direction
        • Null
          • stating their will be no difference or direction
      • Validity
        • Truthfulness of the measure and does it measure what it claims to?
        • Internal Validity
          • ability of the study to test the hypothesis it was designed to test. try to control as many variables as possible, stop demand characteristics and experimenter effects
          • to improve single blind technique is used where pp's do not know what condition they are in. also double blind is used so neither pp or experimenter know what condition they are in.
        • External Validity
          • concerned with how well the results of the study can be generalised beyond itself.
          • ecological validity refers to whether we can extend its past the setting
          • population validity refers to whether we can generalise the results past the sample
        • the more the cofounding variables are controlled to improve internal validity, the more the study reduces external
      • Reliability
        • can it be replicates with the same results?
        • external
          • ability to produce the same results each time the test is replicated using the retest method. Can conduct a test of correlation to get reliability
        • Internal
          • asoociated with measures, scale+ altitude and concerned with consistency within a test typically done through inter rater reliability
    • Choosing and drawing graphs
      • Bar Chart (Differences)
      • Scatter Graph(relationships)
      • Contingency table (Chi-squared)
    • Interviews
      • Unstructured
        • +more e. validity because depth and flexibility
        • -takes longer to conduct and quantity and more training needed
        • -may be biased and affect validity
      • Structured
        • +less time consuming and less training needed
        • +Data is already quantitative
        • -may be bias and affect validity
        • -can't gain depth reducing c. validity
    • Case studies
      • in depth study of an individual or group which gathers detailed info about them. this could come from records, interview etc.
      • rich source of meaningful dataand can challenge theories etc
      • difficult to generalise so have low p. validity and hard to replicate
    • Questionnaires
      • Open
        • +can explore subjects as they arise increasing depth and e. validity
        • + collect large amounts of data
        • -time consumingto collect and quanitify
        • low response rate reducing validity
        • social desirability bias
      • closed
        • +quick to do and already quantified
        • +collects large amounts of data
        • -low response rates reducing validity
        • social desirability
        • flexible so reduces e. validity
    • Observations
      • lab-allows the researcher to control the environment and manipulate some of the variables, but lacks e. validity and suffer from investigator effects
      • natural- very realistic, can study behaviours that would not be possible in a lab, however low control and may suffr observer bias
    • content analysis

Comments

No comments have yet been made

Similar Psychology resources:

See all Psychology resources »See all Research methods and techniques resources »