Chapter 12 review

• Simple experiments


  • Involve one independent variable and one dependent variable
• Psychological science hypotheses


  • More complex, involve studying two or more independent variables
• Experiments with one independent variable


  Researchers look for a simple difference, such as the difference between being drunk or sober or the difference between being on a cell phone or not
• Experiments with two independent variables


  Researchers are testing for interactions, asking whether the effect of one independent variable depends on the level of the other one
• Interaction


  A "difference in differences"
• Factorial designs


  • Cross two or more independent variables, creating conditions (cells) that represent every possible combination of the levels of each independent variable
• Factorial designs


  • Can describe multiple influences on behavior; they enable researchers to test their theories and determine whether some manipulation affects one type of person more than another
• Analyzing data from a factorial design


  Look for main effects for each independent variable by estimating the marginal means, then look for interaction effects by checking for a difference in differences (in a line graph, interactions appear as nonparallel lines)
• When there is an interaction effect, it is more important than any main effects found
• Factorial variations


  • The factors can be independent-groups or within-groups variables
  • The factors can be manipulated (independent) variables or measured, participant variables
• When a factorial design has three or more independent variables, the number of interactions increases to include all possible combinations of the independent variables
• In a design with three independent variables


  The three-way interaction tests whether two-way interactions are the same at the levels of the third independent variable
• In empirical journal articles, the type of design is given in the Method section
• In popular media stories, factorial designs may be indicated by language such as "it depends" and "only when," or descriptions of both participant variables and independent variables