Transcript Chapter 8
True experimental method, all extraneous
variables are controlled.
Create groups that differ in the levels of the
Variables are kept constant through direct
control or randomization
If scores of the two groups are different, then the
experimenter can reasonably assume the
difference is due to the manipulated variable.
Confounding Variables-one which varies
along with the independent
variable…confounding the results.
Internal validity-When the results of an
experiment can confidently be attributed to
the effect of the I.V.
Independent Groups Design
Repeated Measures Design
Participants are assigned to at least two groups,
experiment and control the effect is measured
Levels of independent variable are chosen: two levels
at least treatment and control, or two levels of
treatment—can have more than one level.
Advantage: easy & inexpensive
Disadvantage: Does not always assure groups were
truly equivalent (experimental & control)
a pre-test is given before the manipulation is
A pre-test can assess whether the groups were
equivalent prior to the manipulation..
Pre-test allows the measurement of the extent of
change in the group or an individual participant.
Advantage: Can assess equivalence, mortality
and extent of change.
Disadvantage: Time consuming and awkward.,
can sensitize the participants to what you are
looking for and they may act differently.
Solomon’s Four Group Design
ability to directly assess the impact of the
pretest with a combination of both the
posttest-only and the pretest-posttest
Half of the participants receive only the posttest
and the other half receive both the pre and post
If there is on impact of the pretest, both of the
posttest scores will be the same.
Independent Groups Design
Different participants are assigned to each
of the condition using random assignment.
Decision to assign an individual to a
particular condition is completely random
and beyond the control of the researcher.
Alternative to the independent groups
design the same individual participants
are in all of the groups.
Fewer research participants needed as each participant
serves in all conditions.
Extremely sensitive to finding statistical significant
Reduces random error due to individual differences as
there is data from the same people in both conditions
Order effects-different conditions must be
presented in a particular sequence which can cause
two types of problems
Practice effects-an improvement in performance
as a result of repeated practice.
Fatigue effects-a deterioration in performance as
the research participant becomes tired, bored or
Carry-over effects-effect of the first treatment
carries over to influence the response to the second
Approaches to Order Effects
Counterbalancing-all possible orders of
presentation are included in the experiment .
Latin square-is a limited set of orders
constructed to insure that each condition
appears at each ordinal position, and that each
condition precedes and follow each condition
Randomized Blocks-basic experimental
procedure is repeated many times.
Time Interval Between Treatments
Other Research Designs
Matched Pairs Design
Developmental Research Designs
Cross Sectional Method