PSYC 217 MIDTERM REVIEW SESSION

1
PSYC 217 MIDTERM REVIEW SESSION

• October 15, 2008

2
NONEXPERIMENTAL METHOD

• Relationships are studied by making observations
  or measure of the variables of interest
• Correlational method
• Relationship is established by looking at how two
  variables vary together
• 2 problems with making causing statements
• 1. hard to determine direction of cause and
  effect
• 2. third-variable problem

3
EXPERIMENTAL METHOD

• One variable is manipulated and the other is
  measured
• Able to say something about the direction of
  cause and effect
• IV cause
• DV effect

4
CONSTRUCT VALIDITY

• Refers to the adequacy of the operational
  definition of variables
• Refers to whether the measure for a certain
  construct adequately represents what is intended
  by theoretical account of the construct being
  measured

5
INTERNAL EXTERNAL VALIDITY

• Internal validity Refers to the ability to draw
  conclusions about causal relationships from our
  data
• Estimates of the degree to which conclusions
  about causes of relations are likely to be true
• External validity Extent to which the results
  can be generalized to other populations and
  settings

6
RELIABILITY

• Refers to the consistency of a measure
• True score
• Actual score on a variable being measured, as
  opposed to the score obtained on the measure
  itself
• Measurement error
• Degree to which a measurement deviates from the
  true score

7
CRITERION-ORIENTED VALIDITY

• Predictive validity Scores on a measure that
  predicts some future behaviour
• Concurrent validity Scores on one measure are
  related with another measure of the same
  construct carried out at the same time
• Convergent validity Scores on one measure are
  related to scores on other measures of the same
  construct
• Discriminant validity Scores on a measure at not
  related to other measures that are supposed to be
  different

8
MEASUREMENT SCALES

• Nominal Categories with no numerical scales
• Ordinal Rank ordering with limited numerical
  values
• Interval Numeric properties are literal with
  equal interval between values
• Ratio Zero indicates absence of variable measured

9
REMINDER!

• 1) You will need a PICTURE ID to turn in your
  exam! Exams will not be accepted and you will
  receive a zero if you do not have a picture ID
  with you.
• 2) You must take the exam in the section you are
  registered for. The two sections have different
  exams. If you take the wrong exam, you will
  receive a zero!
• 3) No hats, baggy clothes, scarves or electronic
  devices will be allowed on exam day. Make sure
  you keep cell phones, pagers, etc. stowed.

10
(No Transcript)