Problem 9 Flashcards
factorial design
each independent variable is referred to as a factor; factorial designs include at least two factors; each factor will include at least two levels
main effect
each effect of an independent variable on a dependent variable averaged across the levels of any other independent variable
interaction
when effect of one independent variable changes depending on the level of the other independent variable
simple main effect
in two-factor design; effect of one independent variable at a given level of the other one
quasi-experimental design
experimental design but use quasi-independent rather than true independent variables
time-series designs
make several observations before the treatment and several after
interrupted time series design
chart changes in behavior as a function of some naturally occurring event rather than manipulate an independent variable
equivalent time samples design
administer and withdraw treatment repeatedly (appropriate when effects of treatment are temporary/transient)
nonequivalent control group design
include time series along with a control group so comparable group subject is observed for the same period
pretest-posttest designs
pre-test before treatment and post-test after to evaluate effect of some change in environment
Solomon four-group design
by eliminating the pre-test you can determine whether the inclusion of it alters the effect of the treatment and you get a simple two-group design
single subject design
expose single subject repeatedly to different treatment and then average across exposures within each treatment
baseline design
individual subjects are observed under each of several conditions and multiple observations of a target behavior are recorded in one phase before the next
baseline phase
assess behavior in the absence of the treatment
intervention phase
assess behavior during application of the the treatment
intrasubject replication
each subject observed under all treatment phases
intersubject replication
multiple subjects –> generality of findings
systematic replications
double checking findings while looking at aspects of the original experiment & adding new ideas
direct replication
replicating/double checking original study exactly
drifting baseline
impossible to stabilize baseline against slow, systematic changes
unrecoverable baseline
baseline levels of performance can’t be recovered (carryover effect)
unequal baseline
baseline differs for every subject, even though they were in same condition
inappropriate baseline levels
particular levels obtained may not be useful for evaluating the effect of subsequent manipulation
multifactor design
manipulate two or more independent variables
multiple baseline design
measure several dependent variables
changing criterion design
systematically change stability criterion to start new baseline
