exam 3 factorial design Flashcards
multiple regression
A statistical technique that can help rule out some third variables, thereby eliminating some alternative explanations and
increasing internal validity.
– It allows you to see if Variable A really does influence Variable B
by “controlling” for the effect of other variables
can multiple regression be used in experiments
multiple regression analysis can also be used in experiments to rule out alternative explanations and strengthen internal validity. experiments can also use multiple independent variables (factorial designs) to test for interactions, test limits of an effect, and test theories.
interaction
the effect of one independent variable depends on the level of the other independent variable
what can test interactions
factorical designs can test limits
Is the effect of Variable A on Variable B limited to one group only?
— Is it limited to a particular situation?
— Checking for moderators!
external validity interactions show moderators
how do factorial designs test theories
the goal of most experiments in psychological science is to
test hypotheses derived from theories
* theories make statements about how variables interact with
one another
* the best way to study how variables interact is to combine
them in a factorial design and see whether results are consistent with theory
ex: why does alcohol increase aggression?
* Theory 1: alcohol impairs the
brain’s executive functioning
* Theory 2: people cognitively
associate alcohol with aggression
– thinking about alcohol primes
people to think about aggression
In a factorial design with 2 IVs and 1 DV, there will be three results to interpret…
main effect of first IV
main effect of second IV
interaction between two IVs
what is a main effect
the overall effect of one IV on the DV, averaging over the other IV
which is more important the main effects or the interactions
the interaction is almost always more important
