Gravetter and Forzano (2017) chap.

9
 Questions:
1. When does a researcher use “Within-Subjects Design”?
2. Explain the advantages and disadvantages of "Within-
Subjects Design" compared to "Between-Subjects Design"?
3. What validity threats will affect “Within-Subjects Design”?
4. What control techniques can be used to overcome these
validity threats?
5. Explain the difference between "Complete
Counterbalancing" and "Partial Counterbalancing"?
Outline:
1. Within-Subjects Experiments and Internal Validity
2. Dealing with Time-Related Threats and Order Effects
3. Comparing Within-Subjects and Between-Subjects Designs
 Characteristics of Within-
Subjects Designs…
 …uses a single group of
participants and tests or
observes each individual in
all of the different treatments
being compared.
 Stephens, Atkins, and Kingston (2009):
The Effect of Swearing on the Experience of Pain
In the study, participants were asked to place one hand in icy
cold water for as long as they could bear the pain.
Treatment-1 Treatment-2

the participants were told the participants repeated a

to repeat their favorite neutral word.
swear word over and over The results clearly showed that swearing
for as long as their hands significantly increased pain tolerance and
were in the water. decreased the perceived level of pain.
Each participant started in one condition and, after a brief rest, repeated the ice
water plunge switching words to the other condition. (1  2 or 2  1)
 Stephens, Atkins, and Kingston (2009):
The Effect of Swearing on the Experience of Pain
Four basic elements of 1. What is the IV of the study and
an experimental study: the manipulation?
1.Manipulation. 2. What is (are) the DV(s) and how
2.Measurement. to measure the DV?
3.Comparison. 3. What is the design of the study?
4.Control. 4. What are the EVs and how to
control them?
 Within-subjects experimental design or
repeated-measures experimental design
In a within-subjects experimental design…
…the same group of individuals participates in every
level of the independent variable so that each
participant experiences all of the different levels of the
independent variable.
Note: the within-subjects design is also well suited to
nonexperimental types of research that investigate
changes occurring over time.
 Threats to Internal Validity of Within-Subjects Experiments

2 major sources of potential confounding for a within-subjects design:

1. from environmental
2. from time-related:
 History

 Maturation

 Instrumentation: (instrumental bias or instrumental decay)

 Regression toward the mean: (statistical regression, or regression

toward the mean)
 Order effects (practice, fatigue, and carry-over effects)
Separating Order Effects and Time-Related Factors
Order Effect
Other time
related factors
Progressive Error
Carryover Effect
Example:
Example:
Practise Effect
Contrast Effect • History
and Fatigue
• Maturation
• Instrumentation
• Regression
 Progressive error: Carryover effect:
refers to changes in a participant’s occur when one
behavior or performance that are treatment condition
related to general experience in a produces a change in the
research study but not related to a participants that affects
specific treatment or treatments. their scores in subsequent
Example: practice effects and treatment conditions.
fatigue. Example: contrast effect
The experience of being tested in one treatment may explain why
the participants’ scores are different in the following treatment.
Order Effects as a Confounding Variable
 Order Effects as a Confounding Variable
 The individual participants (and the group) mean show
consistently higher scores (+5) in the second treatment.
 These data could lead the researcher to conclude that there
is a significant difference between the treatments when, in
fact, no such difference exists.
 Thus, order effects, like any confounding variable, can
distort the results of a research study.
 Dealing with Time-Related Threats and Order Effects
 Within-subjects designs can control environmental
threats to internal validity using the same techniques
that are used in between-subjects designs by (1)
randomization, (2) holding them constant, or (3)
matching across treatment conditions.
 Time-related factors and order effects, require special
attention and new strategies for control.
some of the methods for dealing with order effects and
time-related threats…
 Controlling Time
 Switch to a Between-Subjects Design
 Counterbalancing
 Counterbalancing:
Matching Treatments with Respect to Time
…is defined as changing the order in which treatment conditions
are administered from one participant to another so that the
treatment conditions are matched with respect to time.
 Use every possible order of treatments with an equal
number of individuals participating in each sequence.
 The purpose of counterbalancing is to eliminate the
potential for confounding by disrupting any systematic
relationship between the order of treatments and time-
related factors.
Counterbalancing and Order Effects
 Counterbalancing - - Order Effects
 The process of counterbalancing is usually discussed in
terms of order effects.
 Counterbalancing prevents any order effects from
accumulating in one particular treatment condition
between treatments (no single treatment has any special
advantage or disadvantage).
 Counterbalancing does not eliminate the order effects;
they are still embedded in the data (and they can still
create problems).
 Limitations of Counterbalancing
 Counterbalancing and Variance
High variance within treatments decreases the likelihood
that a research study will obtain significant differences
between treatments. Thus, in situations in which order
effects are relatively large, the process of counterbalancing
can undermine the potential for a successful experiment.
 Asymmetrical Order Effects
 Counterbalancing and the Number of Treatments
 Limitations of Counterbalancing
 Counterbalancing and Variance
 Asymmetrical Order Effects
It is definitely possible that one treatment might produce
more of an order effect than another treatment.
In such situations, the order effects are not symmetrical, and
counterbalancing the order of treatments does not balance
the order effects.
 Counterbalancing and the Number of Treatments
 Limitations of Counterbalancing
 Counterbalancing and Variance
 Asymmetrical Order Effects
 Counterbalancing and the Number of Treatments
 Complete counterbalancing
If the number of different treatment conditions is identified as
n, then the number of different sequences is n! (n factorial).
To completely counterbalance with four treatment conditions,
the researcher must divide the participants into 24 equal-sized
groups and assign one group to each of the 24 different
sequences.
 Limitations of Counterbalancing
 Counterbalancing and Variance
 Asymmetrical Order Effects
 Counterbalancing and the Number of Treatments
 Partial counterbalancing
Uses enough different orderings to ensure that each
treatment condition occurs first in the sequence for one group
of participants, occurs second for another group, third for
another group, and so on.
With four treatments, for example, this requires only four
different sequences, such as: ABCD,CADB, BDAC, DCBA.
 Latin square - - Partial counterbalancing
Example: 4 treatments A B C D
DABC
CDAB
BCDA
 One method for improving the square is to use a random
process to rearrange the columns, then use a random
process to rearrange the rows.
 The resulting rows in the square should provide a better set
of sequences for a partially counterbalanced research study.
Comparing Within-Subjects and Between-Subjects Designs

 Advantages of Within-Subjects Designs

 it requires relatively few participants in comparison to
between-subjects designs.
 it essentially eliminates all of the problems based on
individual differences (that are the primary concern of a
between-subjects design).
 Disadvantages of Within-Subjects Designs
Comparing Within-Subjects and Between-Subjects Designs
 Advantages of Within-Subjects Designs
 Disadvantages of Within-Subjects Designs
 a series of treatment conditions, with each treatment
administered at a different time  time-related factors
 participant attrition: some of the individuals who start the
research study may be gone before the study is completed.
 it is advisable to begin the research study with more
individuals than are actually needed.
 Choosing Within-Subjects or Between-Subjects Designs
Three factors that differentiate the designs are:
 Individual differences.
 Time-related factors and order effects.
 Fewer participants.
 Matched-Subjects Designs
…uses a separate group for each treatment condition, but each individual
in one group is matched one-to-one with an individual in every other
group.
 The matching is based on a variable considered to be particularly
relevant to the specific study.
 Example: compare different methods for teaching mathematics.
The researcher might give a mathematics achievement test to a large
sample of students, then match individuals based on their test scores.
 Thus, if Tom and Bill have identical math achievement scores, these two
students can be treated as a matched pair, with Tom assigned to one
teaching method and Bill assigned to the other.
 Matched-Subjects Designs
 If the study compares three treatments, then the researcher
needs to find triplets of matched individuals.
 The goal of a matched-subjects design is to duplicate all the
advantages of within and between-subjects designs without the
disadvantages of either one.
 It is possible to match participants on more than one variable.
A matched-subjects design attempts to eliminate the problems
associated with between-subjects experiments (individual
differences) and the problems associated with within-subjects
experiments (order effects).