L9 BETWEEN-SUBJECTS

• experimental design - general structure of the experiment used to answer many kinds of research questions
• 3 aspects of experiment that play the biggest part in determining the design:

  • number of IV
  • number of treatment conditions needed to make a fair test
  • whether same or different subjects are used in treatment conditions
• between-subjects design - different subjects take part in each conditions of the experiment
• within-subjects design - same subjects take part in more than one treatment conditions of the experiment
• external validity - increases when random sampling procedure is highly desirable
• small sample - if individuals in the population are all very similar to one another on the DV
• large sample - when individuals are likely to be quite different
• statistical tests - used to make comparisons of subjects' behavior under different treatment conditions
• effect size - statistical estimate of the size or magnitude of the treatment effect
• larger effect size - fewer subjects needed to detect a treatment effect
• power charts - estimate the minimum number of subjects needed for each treatment group
• two-group design - when only 2 treatment conditions are needed, the experimenter may choose to form 2 separate groups of subjects
• 2 variations of two-group design:

  • two-independent-groups design
  • two-matched-groups design
• two-independent-groups design - subjects are placed in each of 2 treatment conditions through random assignment
• random assignment - every subject has an equal chance of being placed in any of the treatment conditions
• confounding - occurs when subjects are not randomly assigned to treatment groups
• experimental condition - apply a particular value of our IV to the subjects and measure the DV
• experimental group - subjects in an experimental condition
• control condition - used to determine the value of the DV without an experimental manipulation of the IV
• control group - subjects in a control condition
• control condition - no-treatment condition
• two-experimental-groups design - used to look at behavioral differences that occur when subjects are exposed to 2 different values or levels of the IV
• two-independent-groups - used when there is only one IV and if the hypothesis can be tested with 2 treatment conditions
• two-matched-groups design - there are also 2 groups of subjects but the researcher assign them to groups by matching or equating them on a characteristic that will probably affect the DV
• precision matching - we insist that the members of the matched pairs have identical scores
• range matching - we require that the n=members of a pair fall within a previously specified range of scores
• smaller range - more similar the subjects must be on the matching variable
• rank-ordered matching - subjects are simply rank ordered by their scores on the matching variable and subjects with adjacent scores them become a matched pair
• 3 matching procedures:

  • precision matching
  • range matching
  • rank-ordered matching
• matching procedures - useful when we have a very small numbers of subjects because there is a greater chance that randomization will produce groups that are dissimilar
• multiple-groups design - there are more than 2 groups of subjects and each group is run through different treatment condition
• multiple-independent-groups design - subjects are assigned to the different treatment conditions at random
• pilot study - pretest selected levels of an independent variable before conducting the actual experiment
• block randomization - creates treatment blocks containing one random order of the conditions in the experiment, subjects are then assigned to fill each successive treatment block
• placebo group - a control condition in which subjects are treated exactly the same as subjects who are in the experimental group, except for the presence of the actual drug, prototype of a good control group