Methodology

• Reliability


  The extent to which an assessment tool can produce results consistently, each time it is used
• Test re-test reliability


  • A measure of reliability obtained by administering the same test twice over some time to a group of individuals
• Parallel-forms reliability


  • A measure of reliability obtained by administering different versions of an assessment tool to the same group of individuals
• Split-half reliability


  • Determined by dividing the total set of items related to a construct of interest into halves and comparing the results obtained from the 2 subsets of items thus created
  • Involves dividing the original test into 2 halves and examining the correlation between them
• Inter-Rater Reliability


  • A measure of consistency used to evaluate the extent to which different judges agree in their assessment decisions
  • Used when data is collected by researchers assigning ratings scores or categories to one or more variables and it can help mitigate observer bias
• Validity


  Refers to the extent to which an assessment tool actually measures what it is designed to measure
• Content Validity


  • Evaluates how well an instrument covers all relevant parts of the construct it aims to measure
• Construct


  A theoretical concept, theme, or idea based on empirical evidence, it's a variable that's usually not directly measurable, such as time
• Criterion-related validity


  • Evaluates how accurately a test measures the outcome it was designed to measure
  • Shows how well a test correlates with an established standard of comparison call a criterion
• Construct Validity


  • The extent to which your test or measure accurately asses what it's supposed to do
• Internal validity


  • The degree of confidence that the casual relationship you are testing is not influenced by other factors or variables
• External Validity


  • Asks whether the findings of a study can be generalised to patients with characteristics that are different from those in the study
• Graphs


  • Labeled axis
  • Title
  • Scale (even)
  • Units
  • Plotted data
• Positive correlation


  Relationship between 2 variables in which both variables move in the same direction
• Negative correlation


  Relationship where 2 variables increase in one variable is associated with a decrease in the other
• Zero correlation


  Exists when there is no relationship between 2 variables
• Prediction


  If there is a relationship between 2 variables we can make predictions about one from another
• Concurrent validity


  • Correlation between a new measure and an established measure
• Test-retest reliability


  • Are the measures consistent?
• Inter-rater reliability


  • Are observers consistent?
• Correlation coefficients


  When studying things that are difficult to measure, we expect the correlation coefficients to be lower. When we are studying things that are easy to measure, such as economic status, we expect higher correlations
• Causation


  One variable causes the other variable
• Correlation


  A relationship between variables, however does not automatically mean that the change in one variable is the cause of the change in the value of the other variable. A correlation only shows if there is a relationship between variables
• Correlation does not always cause causation, a third variable may be involved
• Observational study


  • An individual observing another individual or a group of people in a natural environment, and recording observations about the behaviour they witness
• Longitudinal study


  • Investigates a group of people over a period of time
• Correlation study


  • Examines whether a relationship exists between two or more variables without the researcher manipulating any of them
• Ethics


  What is deemed as acceptable human behaviour to complete goals
• Ethics


  • Not a question of right but a balance of interests between the interests of the participants and the value of research
• Guidelines


  What you can and can't do with participants
• Ethical review


  1. Research plan must be submitted to an ethics committee for approval

  2. Ethics community examines potential benefits of the research to society

  3. Benefits are weighted against potential risks
• Privacy


  For example date of birth or phone number
• Confidentiality


  Telling someone information and entrusting them to not tell others
• Roles of experimenter


  • Protect participants' physical + psychological welfare
  • At no time shall a researcher conduct a study that causes severe distress to participants. If found the research must stop and the participants will be offered counselling
  • The experimenter must be professional consistently and be fair/just to everyone
  • The experimenter must weigh the risks of the experiment against the benefit to society when applying to do research
  • Consider the location of the experiment and the care of the participants
• Participant rights


  • Confidentiality
  • Right to privacy
  • To access, storage, and disposal of information collected about them related to the research
  • Voluntary participation
  • Withdrawal rights
• Voluntary participation


  • Ensures a participant willingly decides to take part in the experiment
  • Participants must not experience any pressure or coercion to participate, nor threatened
• Withdrawal rights


  • The right of a participant to cease their participation in a study at any time without consequence
  • Applies to follow-ups and post-research
  • In this case, the results of said participant would need to be removed
• Informed consent


  1. Must be obtained before an experiment starts

  2. Must be written, informed permission from each participant

  3. Informed means they have been given all information regarding the experiment

  4. A consent form must inform participants about their rights, any possible harm they could encounter, and the research procedure involved

  5. Parent or guardian permission if the participant is under 18
• Deception


  • Should never occur unless necessary
  • Only ever used if information about an experiment beforehand might influence their behaviour. Therefore it messes with potential results
  • Must be used with caution
  • If used, researchers must ensure that all participants are thoroughly debriefed
• Debriefing


  1. Participants are informed of the study's true purpose once the experiment is over

  2. The researcher must explain any and all deception related to the experiment

  3. Participants must also have the chance to gain access to the information about the study