REPEATED MEASURE DESIGN IN EXPERIMENTAL RESEARCH

A. Introduction

Repeated Measures Designs (RMD) are one of the most frequently studied and applied

designs in a variety of applied fields. A design in which the same experimental

unit is repeatedly observed under multiple treatments is called
repeated measures design.
A repeated-measures design is using the same participants for all of
your experimental conditions and takes part in each condition of the
independent variable (Field, 2011). This means that each condition of the
experiment includes the same group of participants. In contrast to an independent groups design,

this is design in which you have same groups of participants for the
different experimental conditions so that each participant is exposed
to every condition (Howitt & Cramer, 2011).
To establish an association between an independent variable and a dependent variable,
true experimental designs have at least two groups. One group is experimental group which
receives some treatment or manipulation of the independent variable. The second group is the

control group which does not receive the treatment. As repeated measures design is
one of the type of experimental designs therefore in repeated
measures design each participant is part of both experimental and
control group (Howell, 2009). Within the many branches of the social and
behavioral sciences the repeated measures model is one of the most frequently used and applied
designs. This stems largely from the general practice of wanting to observe a certain behavior
over a given period of time. For many developmental psychologists the longitudinal
research design is best option which lends itself to gathering insight into the progressive nature
of the human psyche.
In this type of design, each subject functions as an experimental block. A block is a
categorical variable that explains variation in the response variable that is not caused by the
factors that you really want to know about. You use blocks in designed experiments to minimize
bias and variance of the error because of these nuisance factors.

In repeated measures designs, the subjects are their own controls because the model
assesses how a subject responds to all of the treatments. By including the subject block in the
analysis, you can control for factors that cause variability between subjects. The result is that
only the variability within subjects is included in the error term, which usually results in a
smaller error term and a more powerful analysis.

A common example is a pre- and post-test of the knowledge level of participants

attending a course of lectures. The following examples illustrate a range of clinical situations
where such studies may be considered:
 In a clinical trial of pharmacokinetics of a drug blood samples may be taken hourly
for 12 hours after its administration. So the data for an individual subject consist of
a series of blood concentration levels.
 During the course of a study on treatments for the relief of asthma, a subject’s
forced expiratory volume (FEV) might be measured at weekly intervals to assess the
efficacy of treatment.
 Preterm babies are weighed twice a week to monitor their rate of growth. A
pediatrician may decide to put them on two different feeding regimes and compare
growth rates in different groups.

A repeated measures design is a variation of experimental design is the situation

where all treatments (X1, X2, etc.) are administered to all subjects. Thus, each individual
(S1, S2, etc.), in essence, serves as his or her own control and is tested or “observed” (O), as
diagrammed below for an experiment using n subjects and k treatments. Note that the diagram
shows each subject receiving the same sequence of treatments; a stronger design, where feasible,
would involve randomly ordering the treatments to eliminate a sequence effect.

S1 (Subject 1) X1O --- X2O-----XkO.

S2 (Subject 2) X1O----X2O ----XkO.

Sn (Subject n) X1O----X2O ----XkO.

Examples

1. A study by Williams and Nguyen (2016) used repeated measure design in their research
investigating Near-peer teaching in paramedic education. In this study, Near-peer teachers
were invited at the commencement of semester and could allocate themselves via a timetable
to any first-year tutorial session. A one-hour overview was provided to all near-peer teachers
prior to teaching their peers. This overview included aims of NPT, approaches to small-group
teaching and employability skills such as listening, communication, and dealing with
conflict. Each near-peer encounter was scheduled on Fridays (three hour sessions) and was
supervised by a faculty tutor and in classrooms involving 8–10 learners; near-peer teachers
taught various fundamental clinical skills including; manual handling techniques, primary
assessment, vital signs assessment including perfusion and respiratory status assessments,
and Glasgow Coma Scale.
2. Caird and Martin (2014) in their research titled Relationship-focused humor styles and
relationship satisfaction in dating couples used repeated measures design. In this study, each
participant completed a diary comprising Positive and Negative Quality in Marriage Scale
and Daily Humor Styles Questionnaire. The first diary was completed in initial group testing
sessions with 1 to 8 individuals attending each session. Following the initial group session,
email messages were sent to the participants every 3 to 4 days (i.e., twice per week) asking
them to complete the next diary on a secure website. Participants were sent a follow-up email
message approximately five months after their participation in the group testing session and
asked to indicate whether or not they were still in dating relationships with their partners.
3. Another recent fMRI study was done by Chung et al. (2016) about the Influence of Menstrual
Cycle and Androstadienone on Female Stress Reactions. In this study repeated measure
design was used. The sequence of three conditions (rest-control-rest-stress) in a block design
was presented in two blocks pre-feedback and post-feedback. In the rest condition, a black
fixation cross was presented. In the control condition, participants were instructed to solve
the arithmetic problems and respond as quickly as possible. In the stress condition, social
evaluative threat and sense of uncontrollability were increased by variable time pressure and
performance monitoring on a visual scale.

Types of Repeated Measures Design

Repeated measures designs come in several types: split-plot, change over, sources of
variability, and longitudinal studies.

Split Plot Designs are extremely popular in design of experiments because they cover a
common case in the real world: when you have a factor that you want to study but can’t change
as often as your other factors (agricultural studies). You may visit the following link for split plot
design example.
https://www.statisticshowto.com/split-plot-design/?
__cf_chl_captcha_tk__=1f9bdd8969b50f65f551db2dd481824fd4d5299b-1617423168-0-
AQtfeIbMkg9BB_ZuZVytUpbYR2g4UyhKqm_4RQ4Ui0mxvVioZ7HsYa1yPEbvTMN3KzIDg
7hiXRlbA6J9wAJItZyOXk6Qzi-
zdUS1kQQffWNGc3mlg_LSic31IFR30wPb5u1wsqjsS7gs4h9JWOTYzo848BwhIDaY7hLmwv
kOh0y4Y5FgJX1iHNHD5KPl4qh4HepaiklcOoHXo3npc0mT13uSRSML4VjASKf64F84dhCsC
cgF02SkfxefMaxkBmbtazY5z_Pt1mcmwHuGPadjIE5w3hIG5B_b8WZOyBqweHwLgGr6FoRl
k3txqfcpAQOm953xqmQG8K6_gt15mhOD_aq3X7X344wVbrgxKs1ys_utJ_utxvkBTGr25yKp
usJaW7d09JvWGC3Dwsf6oCf7QH9M4uW14VXvsDJzDr3qH9xZc--k2HDg7NJiDs-
fwXFeuRHI3ffNNue9cNvX_r625FaWzwQBj7NNOYTreYdzhcNQQb8FFbaFR-1sLZ4FUM-
vrnl7jpt5oHs96AVfjblyp16UERTBYYydADTEDu33vtYC_2COIZoUbi6RhM7hkXIGZSxnZkx
Q5TP5BEk-ZBXaSY2BZvGbdBnWwBjNvSw-xNSuf4wdsRWTuRdMOa7Lu5xjzQ

Change over Designs may be used when testing two types of drugs. First, half of the
people are given drug A and the others are given drug B. Then drug A and drug B are switched
and the experiment is rerun. This design is a repeated measures experiment because every person
will have two measures, one for drug A and one for drug B (Kotz & Johnson, 1988).
G1-A G2-B G1-B G2-A
Source of Variability Studies When control and treatment groups consist of different
individuals the changes brought about by the treatment may be masked by the variability
between subjects. When to rule out variability between subjects. It may include taking several
randomly selected items from a manufacturing process and allowing several people to test each
one, possibly over several days (Kotz & Johnson, 1988).

Longitudinal Studies is in which the dependent variable is measured at several time

points for each subject, often over a relatively long period of time.

B. When to use Repeated Measures Design

Repeated measures design is a type of experimental research so this design is basically

use in experiments in which a researcher have to make a prediction. In an experimental
research, experimenter’s interest in the effect of environmental change, referred to as
“treatments,” demanded designs using standardized procedures to hold all conditions constant
except the independent variable. A repeated measures design is a variation of experimental
design is the situation where all treatments are administered to all subjects. In repeated
measure design, instead of having one score per subject, experiments are frequently conducted in
which multiple scores are gathered for each case.

There are some conditions as well when we use repeated measures design;

 Measuring performance on the same variable over time for example looking at
changes in performance during training or before and after a specific treatment
 Measuring same subject multiple times under different conditions for example
performance when taking Drug A and performance when taking Drug B
 Measuring same subjects who provide measures/ratings on different characteristics for
example the desirability of different characteristics of interpersonal relationships
 Measuring how we could do some repeated measures as regular between subjects designs
for example randomly assign to drug A or B

C. Steps Involved in Repeated Measures Design

Following are the steps involved in administering a simple repeated measures design;

Step 1: A sample of participants is selected randomly from the population.

Step 2: All participants receive the same treatments (usually called “conditions”).

Step 3: Each participant is undergone through a pretest in a control condition.

Step 4: Each participant is given all possible treatments and scores are analyzed.

Step 5: A posttest is conducted and scores are examined.

Step 6: Scores are analyzed using appropriated “repeated measures” stats tests.

(Shuttleworth, 2009)

D. Advantages and Disadvantages of Repeated Measures Design

Advantages
i. Reduces Individual Differences:
A benefit of using repeated-measures (using the same participants for both manipulations) is
it allows the researcher to exclude the effects of individual differences that could occur
if two different people were used instead (Howitt & Cramer, 2011). Factors such as IQ,
ability, age and other important variables remain the same in repeated-measures as it is the
same person taking part in each condition (Field, 2011). This is one of the disadvantages of
using independent groups.

ii. More statistical power:

Repeated measures designs can be very powerful because they control for factors that
cause variability between subjects. Using same participants in experimental and control
group means that confounds caused by participant variables will be eliminated. Repeated
subject designs are commonly used in longitudinal studies, over the long term, and in
educational tests where it is important to ensure that variability is low.

iii. Fewer subjects:

Because of its greater statistical power, a repeated measures design can use fewer subjects
to detect a desired effect size. Further sample size reductions are possible because each
subject is involved with multiple treatments.  For example, whereas repeated-measures
may only need 20 participants, independent groups would need 20 participants for each
condition (Howitt & Cramer, 2011). 

iv. Quicker and cheaper:

Fewer subjects need to be recruited, trained, and compensated to complete an entire
experiment. Also, fewer resources are required.

v. Assess an effect over time: 

Repeated measures designs can track effect overtime, such as the learning curve for a
task. In this situation, it’s often better to measure the same subject at multiple times
rather than different subjects at one point in time for each.

Disadvantages
Repeated measures designs have some disadvantages compared to designs that have
independent groups. The biggest drawbacks are known as order effects, and they are caused
by exposing the subjects to multiple treatments. Order Effects can take form of;

i. Practice Effects:
Practice effects occur when subjects change systematically during the course of an
experiment (Tanguma, 1999). Effects could be due to repetition causing participants’
results to improve because they were given more chance to practice and become
familiar with the task (Collie, Maruff, Darby & McStephen, 2003).

ii. Boredom/ Fatigue Effect:

Tanguma(1999) indicated that a negative practice effect may result from fatigue or
boredom. He recommended that researchers lengthen the rest period between
measurement occasions to manage fatigue and provide incentives as a technique to
motivate participants throughout the course of the experiment.

iii. Drop-outs:
Repeated measures design takes long time and participants have to take part in both
conditions so drop outs are likely. With increasing the interval between two events,
there is more likelihood of withdrawal of participants.

Managing the Challenges of Repeated Measures Design

Counterbalancing:

Order effects can be reduced by counterbalancing (Field, 2011). In the counterbalancing

procedure, half the participants will first perform the task with the Independent variable
present (experimental condition) and then perform the task with the Independent variable
absent (control condition). The other half of the participants will experience the conditions
in the reverse order. For example, half the participants would be exposed to control A first and
then control B, and the other half of participants exposed to control B and then control A (Howitt
& Cramer, 2011). Random selection should be used to decide which participants perform the
tasks in which order. The results should then be less affected by factors such as boredom and
practice.