PSYC 270 FINAL

• Covariance


  One of the three criteria for establishing causation
• Temporal precedence


  One of the three criteria for establishing causation
• Internal validity


  One of the three criteria for establishing causation
• Multivariate designs


  • Involve more than two measured variables
  • Longitudinal designs help address temporal precedence
  • Multiple regression analyses help address internal validity
• Types of correlations in longitudinal designs


  • Cross-sectional correlations
  • Autocorrelations
  • Cross-lag correlations
• Cross-sectional correlations


  Test of whether 2 variables measured at the same point in time are correlated
• Autocorrelations


  Correlation of each variable with itself across time
• Cross-lag correlations


  Correlation of degree to which an earlier measure of one variable is associated with a later measure of the other variable
• Possible patterns in cross-lag correlations


  • Not significant
  • One correlation significant, the other flipped
  • Both correlations significant
• Longitudinal designs can provide some evidence for causation by fulfilling three criteria: covariance, temporal precedence, and internal validity
• In many cases participants cannot be randomly assigned to a variable, as it may be unethical or people cannot be assigned to preferences
• Regression results


  Indicate whether a third variable explains the relationship
• Beta


  Used to test for third variables
• Multiple regression is not a foolproof way to rule out all kinds of third variables
• Evidence for causality from pattern and parsimony


  • The longer a person has smoked cigarettes, the greater are the chances of getting cancer
  • People who stop smoking have lower cancer rates than people who continue smoking
  • Smokers' cancers tend to be in the lungs and of a particular type
  • Smokers who use filtered cigarettes have a somewhat lower rate of cancer than smokers of unfiltered cigarettes
  • People who live with smokers will also have higher rates of cancer because of their passive exposure to the same chemicals
• Journalists do not always fairly represent pattern and parsimony, as they often selectively present only part of the scientific process
• Mediators


  Variables that explain the relationship between a predictor and an outcome variable
• Moderators


  Variables that affect the strength or direction of the relationship between a predictor and an outcome variable
• Four validities in multivariate designs


  • Internal validity
  • Construct validity
  • External validity
  • Statistical validity
• Independent variable (IV)


  Manipulated variable in an experiment
• Dependent variable (DV)


  Measured, outcome variable in an experiment
• Control variable


  Any variable that an experimenter holds constant
• Experiments establish covariance, temporal precedence, and internal validity
• Types of groups in experiments


  • Control group (no treatment condition)
  • Treatment group(s) (one or more treatment conditions)
  • Placebo group (placebo control group)
• Design confounds are second variables that systematically vary along with the independent variable, providing an alternative explanation for the results
• Selection effects occur when there are systematic differences between the groups in an experiment
• Independent-groups design


  Different groups are placed at different levels of the independent variable
• Within-groups design


  Each participant is presented with all levels of the independent variable
• Posttest-only design


  Participants are measured only after the intervention
• Pretest/posttest design


  Participants are measured before and after the intervention
• Repeated-measures design


  Each participant experiences all levels of the independent variable
• Concurrent-measures design


  Each participant experiences all levels of the independent variable at the same time
• Order effects occur when being exposed to one condition affects how participants respond to other conditions
• Counterbalancing


  A technique to avoid order effects by varying the order in which participants experience the conditions
• Construct validity refers to how well the variables were measured and manipulated
• External validity refers to how well the causal claim can be generalized
• Statistical validity refers to the size, precision, and replicability of the effect
• Internal validity refers to whether there are alternative explanations for the results
• Interaction


  The level of one independent variable depends on the level of another independent variable
• Factorial design


  A design with two or more independent variables