Professional Documents
Culture Documents
Experimental Designs
Experimental Designs
Block Randomization:
• Block randomization balances subject characteristics and potential confounding that occur
during the time in which the experiment is conducted, and it creates groups of equal size.
A common procedure for carrying out random assignment is block randomization. First, let
us describe exactly how block randomization is carried out, and then we will look at what it
accomplishes. Suppose we have an experiment with five conditions (labelled, for
convenience, as A, B, C, D, and E). One “block” is made up of a random order of all five
conditions:
In block randomization, we assign subjects to conditions one block at a time. In our example
with five conditions, five subjects would be needed to complete the first block with one
subject in each condition. The next five subjects would be assigned to one of each of the five
conditions to complete a second block, and so on. If we want to have 10 subjects in each of
five conditions, then there would be 10 blocks in the block-randomized schedule. Each block
would consist of a random arrangement of the five conditions.
Advantages of BR:
o Equal group size
o Control for time related variables
o Balances effects of event
o Balances participant characteristics.
o Block randomization also works to balance other time-related variables, such as
changes in experimenters or even changes in the populations from which subjects are
drawn. For example, a perfectly acceptable experiment could be done drawing
students from both fall and spring semester classes if a block randomization schedule
is used.
Disadvantages of BR:
o Subject loss
o Placebo effect
o Pre-existing differences among participants.
• Causal inferences cannot be made regarding the effects of natural groups variables because
plausible alternative explanations for group differences exist.
Researchers in many areas of psychology are interested in independent variables that are
called individual differences variables, or subject variables. An individual differences
variable is a characteristic or trait that varies across individuals. Religious affiliation is an
example of an individual differences’ variable. Researchers can’t manipulate this variable by
randomly assigning people to Catholic, Jewish, Muslim, Protestant, or other groups. Instead,
researchers’ “control” the religious affiliation variable by systematically selecting individuals
who naturally belong to these groups. Individual differences variables such as gender,
introversion–extraversion, race, or age are important independent variables in many areas of
psychology.
Results of nature group cannot be generalized, as they can’t be manipulated. Every1 has
individual differences. So, what is true for a group cannot be true for everyone
Summary:
Repeated measures Designs:
Repeated measures are designs in which participants goes through all the condition.
Advantages of Repeated measures:
Complete designs:
In complete design, each participant is administered all the condition several times using
different order each time. Thus, each participant can be considered as a complete experiment.
In the complete design, participants are given each treatment enough times to balance
practice effects for each participant. When the task is simple enough and not too time
consuming (such as judging the emotional intensity of photographs), it is possible to give one
participant several experiences with each treatment. In fact, in some complete designs, only
one or two participants are tested, and each participant experiences literally hundreds of
trials.
There are two types of compete design, Block randomization and ABBA counterbalancing.
A) Block randomization
Block randomization is preferred over ABBA counterbalancing when practice effects are not
linear, or when participants’ performance can be affected by anticipation effects.
Block randomization is effective in balancing practice effects, but each condition must be
repeated several times before we can expect practice effects to average out. We should not
expect practice effects to be balanced after two or three blocks—any more than we would
expect sample sizes of two or three in the random groups design to result in comparable
groups.
B) ABBA Counterbalancing
ABBA counterbalancing can be used to balance practice effects in the complete design with
as few as two administrations of each condition. ABBA counterbalancing involves presenting
the conditions in one sequence (i.e., A then B) followed by the opposite of that same
sequence (i.e., B then A). Its name describes the sequences when there are only two
conditions (A and B) in the experiment.
ABBA counterbalancing is appropriately used only when practice effects are linear. If
practice effects are linear, the same amount of practice effects is added to or subtracted from
performance on each successive trial. For instance, if an experimenter wants to test which is
better and easier overum balling or underum. If the researcher first teaches underrun to a
player, he will score less in that condition because hen is new to the game and then if the
researcher teaches overrun, participant will but obvious score a little better because now he is
now a little used to it. So, to balance it out, researcher on the second trial will teach overrun
first and at the last again underrun so that the practice effect is balanced out.
ABBA is ineffective when practice effect for a task are not linear. Nonlinear practice effects
can occur when participants’ performance changes dramatically after exposure to one or more
trials. ABBA is also ineffective when anticipation effects can occur. Anticipation effects
occur when a participant develops expectations about which condition should occur next in
the sequence.
Incomplete designs:
Practice effects are balanced across subjects rather than for subjects in incomplete design. In
incomplete design, participants go through each condition only once. The rule for balancing
practice effects in the incomplete design is that each condition of the experiment must be
presented in each ordinal position (first, second, etc.) equally often.
In the incomplete design, each participant is given each treatment only once. The results for
any one participant, therefore, cannot be interpreted because the levels of the independent
variable for each participant are perfectly confounded with the order in which those levels
were presented. For instance, the first participant in an incomplete design experiment might
be tested first in the experimental condition (E) and second in the control condition (C). If
appropriate balancing is carried out, then we will be in a position to determine whether the
independent variable, not practice effects, influenced the participants’ behaviour. Any
differences in the participant’s performance between the experimental and control conditions
could be due to the effect of the independent variable or to the practice effects resulting from
the EC order. To break this confounding of the order of conditions and the independent
variable, we can administer different orders of the conditions to different participants.
For instance, in a study, Psychologist wanted to study time interval between exercise to
improve mood. There were 4 conditions, Resting, 10min, 20 min, 30 min. They checked
mood before every condition. In participant goes through only once in all 4 days a week.
Researcher collected data about how each condition affected the mood.
Two methods for selecting specific orders to use in an incomplete design are the Latin Square
and random starting order with rotation.
The first type of balancing using selected orders is called the Latin Square. In a Latin Square,
the general rule for balancing practice effects is met. That is, each condition appears at each
ordinal position once. In the Latin Square, condition “0” appears exactly once in the first,
second, third, and fourth ordinal positions. This is true for each condition. Additionally, in a
Latin Square each condition precedes and follows each other condition exactly once. It is
used when there are more than 2 conditions. Each condition proceeds and follows each other
condition exactly once.
Suppose if there are 4 conditions, then n=4. Then, general formula for constructing latin
square is: 1,2,n, 3,n-1,4
Complex Designs:
Complex designs can also be called factorial designs because they involve factorial
combination of independent variables. Factorial combination involves pairing each level of
one independent variable with each level of a second independent variable. This makes it
possible to determine the effect of each independent variable alone (main effect) and the
effect of the independent variables in combination (interaction effect).