Lecture Material

• What are the three tri-council policy (TCPS) statements in Canada?

  1. Canadian Institute of Health Research (CIHR)
  2. Social Sciences and Humanities Research Council of Canada (SSHRCC)
  3. Natural Sciences and Engineering Research Council of Canada (NSERCC)
• What are the six Canadian Psychological Association (CPA)'s ethical principles for psychology research?

  1. Respect for dignity of persons.
  2. Privacy and confidentiality.
  3. Informed consent.
  4. Minimising Harm
  5. Freedom to Withdraw.
  6. Use of Deception.
• What exactly is privacy and confidentiality?

  • Confidentiality: Individual responses kept best secret and use only for the purposes promised by the researcher?
  • Anonymity: When information cannot be connected to people's identity.
• What exactly is informed consent?

  When subjects are informed of all available information about the study so they can make a rational decision to participate. A consent form contains all the elements of informed consent and a place for the participant to sign.
• What is erroneous about informed consent?

  1. Autonomy Issues – The extent to which a participant can understand the information provided (e.g. minors, peoples with disorders and individuals are at risk of coercion).
  2. Deception – Researchers often use passive and active deception when it is called for in an experiment.
• Passive Deception

  When one withholds information due to concern with the participant knowing what the purpose of the study is (the participant's behaviour fulfills the purpose of the study); thus, the data is useless.
• Active Deception

  When researchers misinform participants about the purpose of the study or some other aspect of the study.
• When researchers use deception, what are their responsibilities to protect participants?

  1. Must be justified.
  2. Cannot withhold information that would affect participants' decision to participate in the study.
  3. Researchers have to debrief participants at the end of the study.
• Debriefing

  Occurring after the study, full disclosure of all aspects of the study. Issues such as deception and potential harmful effects are disclose. This ensures the participants do not have any ill-feelings towards the field.
• Reliability

  Stability or consistency of the measurements produced by a specific measurement procedure. This can be expressed by the following formula:

  $measured score =$$true score +$$error.$
• Operational Definition

  A definition of the variable in terms of the operations or techniques used to measure or manipulate it in a specific study.
• How do we Achieve Reliability?

  • Train observers well – be explicit and specific with the instructions and detail regarding the variable being measured.
  • Word questions well – make sure that participants don't get confused with what exactly the question wants.
  • Calibrate and place equipment well.
  • Observe contrast multiple times – we want to have multiple observations of the same variables.
• How can we know how reliable a measure is?

  1. Test-Retest Reliability
  2. Internal Consistency Reliability
  3. Split-Half Reliability
• Test-Retest Reliability

  How consistent a measure is across time; take measures two times and correlation of score at time one with score at time two; scores should be similar.
• Internal Consistency Reliability

  How consistent is the measure across items intended to measure the same concept?;

  • Cronbach's Alpha: Based on the average of all the inter-item correlations *and the number of items in the measure; how the items in the scale correlate with each other and if they correlate highly with each other.
• Internal Consistency Reliability

  How consistent is the measure across items intended to measure the same concept?;

  • Cronbach's Alpha: Based on the average of all the inter-item correlations *and the number of items in the measure; how the items in the scale correlate with each other and if they correlate highly with each other.
  • Split-half Reliability: Splits the test in half computing a separate score for each half, and then calculates a correlation between the two scores.
• Inter-Rater Reliability

  How consistent is the measure when different people are rating?; extent to which raters agree in their observations.
• Reliability indicates what?

  It indicates the amount of error but not accuracy; a measure can be highly reliable but not accurate.
• Construct Validity

  The degree to which the operational definition of a variable accurately reflects the true theoretical meaning of the variable.
• What are the indicators of construct validity as a measure?

  1. Does the content of a measure reflect the theoretical meaning of the construct?:

  • Face and Content Validity

  2. How does this measure relate to other measures and behaviour?

  • Predictive, Concurrent, Convergent, and Discriminant Validity.
• Face Validity

  The content of the measure appears to reflect the construct being measured.
• Content Validity

  The content of the measure captures all aspects of the intended construct.
• Predictive Validity

  Scores on the measure predict behaviour on a criterion measured at a time in the future.
• Concurrent Validity

  Scores on the measure are related to a criterion measured at the same time.
• Convergent Validity

  Scores on the measure are related to other measures of the same construct or similar constructs.
• Discriminant Validity

  Scores on the measure are not related to other measures that are theoretically different.
• What are the properties of the four scales of measurement?

  1. Nominal
  2. Ordinal
  3. Interval
  4. Ratio
• Nominal

  Has no numerical or quantitative properties. Instead, categories or groups simply differ from one another.
• Ordinal

  Allows us to rank order the levels of the variable being studied: rank ordering with numeric values, values are small or larger than the next, interval between items are not known.
• Interval

  Values are smaller or larger than the next, interval between items is known and is meaningful, no true zero point.
• Ratio

  Values are small or larger than the next, interval between items is known and is meaningful, has a true zero point.