BM CH10

• causal claims are generally used to...


  give advice and interventions
• experiment


  the researcher has manipulated at least one variable and measured another
• an experiment needs at least one IV and DV, but may have more than one...


  dependent variable
• the IV tends to be on the _ axis


  x
• control group


  a level of the IV to represent neutral or no treatment
• treatment groups


  any level of an experiment with a control group that is not neutral
• placebo (control) group


  exposed to an inert treatment
• many experiments do not have a...

  clear control group
• manipulating the IV tends to establish...

  temporal precedence
• design confounds


  an experimenter's mistake in designing the IV, a second variable that happens to vary systematically along with the IV
• design confounds point to poor...

  internal validity
• systematic variability


  the levels of a variable coinciding in some predictable way with experimental group membership, creating a potential confound
• unsystematic variability


  in an experiment, when levels of a variable fluctuate independently of experimental group membership, contributing to variability within groups
• generally, unsystematic variability is...

  not a confound, but it may make it difficult to detect differences in the DV
• selection effects


  when the kind of individuals in one level of the IV vary from those in another
• selection effects may occur if...

  participants choose their own group or are picked by some criteria
• selection effects can be avoided by...

  using random assignment or matched groups
• random assignment creates random groups up to...

  98% of the time
• matched groups


  match into pairs and then randomly assign the pairs
• matched groups is random...


  but also keeps groups equal
• con of matched groups

  requires more time, effort and resources
• independent groups design


  different groups of participants given different levels
• independent groups design aka

  between-subjects or between-groups design
• within-groups design


  all subjects presented with all levels
• within-groups design aka


  within-subjects design
• types of independent groups design

  posttest-only, pretest/posttest
• types of within-groups designs

  repeated measures, concurrent measures
• posttest-only design


  randomly assigned IV, tested on DV once
• posttest-only design pros


  more basic, satisfies criteria for causation
• pretest/posttest design


  random assignment to at least two groups, tested on DV twice (before and after)
• pretest/posttest design pros


  can show that random assignment created two equal groups, useful for tracking over time
• repeated measures design


  participants measured on DV multiple times, after exposure to each level IV
• concurrent-measures design


  participants exposed to all levels of the IV at roughly the same time, and a single attitudinal/behavioural preference is the DV
• within-groups advantages


  equivalent groups, participants act as own control, less participants, more efficient
• power


  the probability that a study will show a statistically significant result when the IV truly has an effect
• within-groups on the criteria for causation

  establishes covariance and temporal precedence
• within-groups on internal validity

  no selection effects, concern over design confounds, order effects
• order effects


  exposing to one condition changes how participants react to the other, behaviour not due to current level of IV but the order of the levels
• types of order effects

  practice, fatigue, carryover
• practice effects


  getting better over time through rehearsal