Randomized

Controlled/Clinical Trials
(RCTs)
Lelisa Sena (PhD)
[Link]@[Link]
lelisajitu@[Link]
Jimma University
 Learning outcomes:

By the end of this module, the students should be able to:

✓Explain the different types of interventional study design
✓Describe the methods of subject selection used in interventional
study design

✓Discuss the concepts and principles of randomization blinding in

interventional study designs

✓Explain the data collection and analysis and ethical issues of

interventional studies

✓Apply interventional study design in a practical situation

2
 What are RCTs?

▪ An RCT is a planned experiment designed to assess the

efficacy of an intervention in human beings by comparing
the intervention to a control condition;

▪Epidemiologic experiments are most frequently

conducted in a clinical setting, with the aim of evaluating
which treatment for a disease is better.

▪Such studies are known as clinical trials (the word trial is

used as a synonym for an epidemiologic experiment).

3
 When should we do a trial?
Trials must have:
▪ a rationale based on prior observational data or biological
evidence;
▪ an explicit, testable, and potentially falsifiable hypothesis;
▪ an uncertainty as to whether an intervention is efficacious
(“equipoise”);
▪ Reasonable expectation that benefits will exceed risk;
▪ An intervention that potentially can be randomized.

4
 ▪ It is possible to clearly measure the
intended results;

▪ the size of the target population is

sufficiently large (most experimental
When should models are based around quantitative
we do a trial? inquiry, and require large sample sizes);
... ▪ it is possible (and ethical) to form an
appropriate control or comparison
group;

▪ If necessary research resources and

expertise, or can afford to buy it in.
 Why RCTs? …
▪Observational and quasi-experimental
designs are subject to potential bias and
confounding due to:
▪ Self-selection

▪ Observer bias

▪ Secular trends (e.g., before and after study)

▪The RCT provides the “gold standard” for proof of

concept.
6
What does “controlled” trials imply?
Controlled implies predefined:
➢eligibility criteria
➢specified hypotheses
➢ primary and secondary endpoints (e.g., behavioral
change, HIV incidence) to address hypotheses
➢ methods for enrollment and follow-up
➢ rigorous monitoring mechanism
➢ analysis plans and stopping rules
7
 Why is randomized assignment of
intervention so important?
1. Best assurance that the control group (unexposed)
is a valid substitute population;

2. Only way to control for unknown factors;

3. Facilitates masking of exposure status;
4. Avoids ambiguity of time order of exposure and
outcome (most intervention studies achieve this);

5. Provides a foundation for statistical tests – valid

quantification of uncertainty.
8
 Why is randomized …
▪Covariates are distributed equally across the groups at
baseline

▪Affects both measured and, more importantly, unmeasured

variables

▪The risk of imbalance remains even after properly executed

randomization

➢If randomization has been performed correctly, chance is

the only explanation for any observed difference b/n groups,
in which case statistical tests are considered superfluous.
9
When is it unethical to randomize?
▪ Known effective treatment
▪ Cannot use a placebo (e.g., trials to prevent mother-to-
child HIV transmission). Need to provide standard of care
▪ Personal choice
▪ Cannot randomize very different interventions
▪ For example, trials of different types of contraceptive (e.g.,
pill vs IUD), are ethically questionable because women
have the right to select a method of their choice
▪ (Can randomize within method type e.g., pill A vs pill B).
▪ Risks of new treatment likely to exceed risks of existing
treatment

10
 What elements of a trial can be randomized?

▪Most common unit is individual patient

▪ Sometimes groups are randomized=cluster
randomization
➢ Examples: families, schools, towns, hospitals, communities

➢Worry about contamination in cluster randomization

➢ Special statistical techniques are needed to cope with the
loss of independence of the individual units.

11
Fig. Design of a randomized controll trial, WHO, 1993

12
 [Link]-group RCTs: Participants
are randomly assigned to one of two
or more groups, each receiving a
Design different intervention or placebo.
options of
RCTs: ▪ Each group is followed up for the
same period.
 2. Crossover RCTs: Participants
receive a sequence of different
treatments (or placebo) in a
random order, with a washout
Design period b/n treatments to prevent
options… carryover effects.
Special forms I- Crossover Studies:

✓Subjects begin the study on Treatment A and

later switch to Treatment B;

✓Patients serve as their own control;

✓Variation b/n individuals remains constant;
✓Washout period b/n treatments reduces
residual carryover.

15
Design of a Planned Crossover Trial

16
 3. Factorial RCTs: Participants are
randomly assigned to one of
several groups that receive
Design different combinations of
options …
interventions.
▪This design allows researchers to
study the interaction between
multiple interventions.
 Special forms II- Factorial Design:

▪Use the same study population to test Drug A & Drug B

▪Assume:
➢ The outcomes for each drug are different
➢ Modes of action are independent

▪If you need to terminate the study of Drug A, you can

continue the study to determine the effects of Drug B
instead of beginning an entirely new study.
18
Factorial Design for Studying Effects of
Two Treatments

19
 4. Pragmatic RCTs: These trials are
designed to evaluate the
effectiveness of interventions in
real-life routine practice
conditions, aiming for a high level
of external validity.
Design ➢Unlike explanatory RCTs, which aim
options… to determine whether an
intervention works under optimal
and controlled conditions, pRCTs
focus on how well an intervention
performs in everyday clinical
practice.
 [Link]-World Settings: pRCTs are
conducted in typical clinical
environments with minimal
exclusion criteria, ensuring that the
study population is representative
Key of the patients who will use the
features of intervention in practice.
pRCTs: [Link] Eligibility Criteria: These
trials include a wide range of
participants to reflect the diversity
of the patient population,
enhancing generalizability.
 4. Routine Practice Conditions:
Interventions are implemented
and assessed under usual care
conditions, without the strict
protocols and intensive
Key features monitoring often seen in
of pRCTs… explanatory trials.
[Link]: pRCTs allow for
variations in how the intervention is
delivered, reflecting the flexibility
found in real-world clinical practice.
 [Link] Services Research:
Assessing the impact of healthcare
policies, programs, or service
delivery models.
[Link] Interventions: Evaluating
Application new treatments, medications, or
of pRCTs… therapeutic approaches in
everyday clinical settings.
[Link] Health Interventions:
Testing the effectiveness of
community-based health initiatives
or preventive measures.
 5. Adaptive RCTs: The trial design
allows for modifications to the
trial procedures (e.g., dosage,
sample size) based on interim
Design results.
options …
▪This type of RCT is flexible and can
provide more efficient pathways to
finding effective treatments.
 6. Stepped-wedge RCTs: All
participants eventually
receive the intervention but
at different times.
Design ▪This type of trial is useful when
options … it is not feasible or ethical to
withhold the intervention from
the control group for the entire
study period.
 7. Non-inferiority RCTs: Designed
to demonstrate that a new
treatment is not worse than an
Design existing treatment by more than
options … a specified margin.
▪This type of trial is common when
the new treatment is expected to
offer other benefits (e.g., fewer
side effects, lower cost).
 8. Superiority RCTs: Aim to
demonstrate that one
intervention is superior to
another.
Design ▪ This is the most common type of
options … RCT, used when a new treatment is
expected to be better than the
current standard.
 10. Equivalence RCTs: Aim to
show that two treatments
have no significant difference
in efficacy within a predefined
Design
options … margin.
▪This is often used when two
treatments are believed to be
similarly effective.
 11. Cluster RCTs: Groups or clusters
of participants (e.g., schools,
communities) are randomly
assigned to different
Design interventions.
options… ▪This type of trial is useful when the
intervention is naturally applied at
the group level.
 a. Field Trials
▪In a field trial, the goal is not to study the complications
of an existing disease, but to study the primary
prevention of a disease.
▪For example, experiments of new vaccines to prevent
infectious illness are field trials because the study
participants have not yet been diagnosed with a
particular disease.
▪In a clinical trial, the study participants can be followed
through regular clinic visits, whereas in a field trial, it
may be necessary to contact participants for follow-up
directly at home, workplace, or school.
30
 b. Community Trials:

▪In a community trial, the exposure is assigned to groups

of people rather than singly.

▪For eg., the community fluoridation trials in the 1940s

and 1950s evaluated the effect of fluoride.

▪A community intervention trial that evaluated a program

of home-based neonatal care and management of sepsis
designed to prevent death among infants in rural India
(next slide) .

31
Community Trials...

▪Table: Neonatal mortality in the third of 3 years

after instituting a community intervention trial of
home-based neonatal care in rural Indian villages

RR = 1.7
32
 ▪ C-RCTs are a type of randomized
controlled trial in which groups or
Community clusters of individuals, rather than
Cluster individual participants, are randomly
Randomized assigned to different intervention arms.
Trials ▪ This design is often used in PH research
(C-RCTs): and other fields where interventions are
applied at the group level (e.g., schools,
communities, workplaces) rather than to
individuals.
 [Link] Instead of Individuals:
In C-RCTs, entire clusters (e.g.,
communities, schools, clinics) are
randomized to receive the
Key intervention or control. This
features of approach is particularly useful
C-RCTs: when individual randomization is
impractical or when the
intervention is delivered at the
group level.
 2. Minimizes Contamination: By
randomizing clusters rather
than individuals, C-RCTs help
to prevent contamination,
Key features where individuals in the
of C-RCTs: control group might be
indirectly exposed to the
intervention.
 3. Analysis of Group Effects:
The analysis focuses on
the effect of the
intervention on the
Key clusters, accounting for
features intra-cluster correlation
of C-RCTs (similarities among
individuals within the
same cluster).
 [Link] Health Interventions: For example,
evaluating the impact of a new sanitation
program on reducing disease incidence
across different villages.

[Link] Interventions: Assessing the

effectiveness of a new teaching method or
Applications:
curriculum implemented in different
schools.

[Link] Delivery: Studying the impact

of different healthcare practices or policies
applied in various clinics or hospitals.
 [Link] Selection: Identify and select
the clusters (e.g., communities, schools)
that will participate in the trial.

[Link]: Randomly assign

clusters to the intervention or control
Steps group.
involved: ▪ This can be done using simple
randomization, stratified
randomization, or matched-pair
randomization to ensure balance
between groups.
 3. Intervention Delivery: Implement the
intervention in the designated clusters while
ensuring that the control clusters do not
receive the intervention or receive a standard
treatment.
Steps [Link] Collection: Collect data from individuals
involved within each cluster, focusing on relevant
outcomes before and after the intervention.
… [Link]: Analyze the data, accounting for the
clustering effect. Statistical methods such as
mixed-effects models or generalized estimating
equations (GEEs) are commonly used to account
for intra-cluster correlation.
 [Link]-World Application: C-RCTs are
particularly useful for evaluating
interventions in real-world settings
where individual randomization is
impractical or impossible.
[Link] of Contamination: By
randomizing entire clusters, the risk of
Advantages: contamination between intervention
and control groups is minimized.
[Link]-Relevant Results: The results
from C-RCTs are often directly applicable
to policy and practice, making them
valuable for decision-makers.
 ➢Nature of the intervention (e.g., mass
media campaign, population-level
interventions)
➢ Acceptability and reduced stigma
(everyone gets the same treatment
within a cluster)
➢Can reduce participant self-selection
Advantages… → maximize generalizability
➢Can get data on many nested
population subgroups
➢Allows assessment of population-level
effects (Population Attributable
Fraction)
 1. Intra-Cluster Correlation: Individuals within
the same cluster are likely to be more similar
to each other than to individuals in other
clusters, which can complicate statistical
analysis and require larger sample sizes to
achieve adequate power.
Challenges:
2. Ethical Considerations: Gaining consent
from entire clusters and ensuring the ethical
treatment of all participants can be complex.

3. Implementation Complexity: Delivering and

maintaining the intervention across different
clusters can be logistically challenging.
 4. Cluster randomization more
vulnerable to lack of comparability
between study arms than individual
randomization (fewer units of
randomization, more correlated
characteristics within members of
Challenges… clusters)

5. Cluster randomized trials increase

sample size requirements and are
less efficient than individual
randomized trials due to intra-cluster
correlation.
Example of a CCRT

44
 c. Clinical Trials
▪A clinical trial is a prospective research study that is
aimed at testing the effectiveness of a new
intervention, usually by comparing it to another
established treatment or to no treatment (a placebo).
▪The ‘intervention’ can be a drug, a medical device, a
surgical procedure or any other therapy aimed at
improving health in some way.
▪Most clinical trials have two or more ‘arms’ (‘multiple-
arm’ studies), but a clinical trial can also have one arm
(‘single-arm’ study).

45
Design and conduct of clinical trials:
1. Define the source population
2. Define the study population
▪ Check weather the proposed experimental population is
sufficiently large to achieve the required sample size for
the trial.
▪ Choose population that will experience a sufficient
number of endpoints to permit meaningful comparison
▪ Likelihood of obtaining complete and accurate follow-up
information for the period of trial.
46
Design and conduct of clinical trials…
3. Allocation of study groups:
▪ Allocation into either group must be done by random.
✓ known and unknown potential confounders will be
equally distributed between the groups.
✓ Randomization can provide a degree of assurance about
the comparability of the study groups that is simply not
possible in any observational design.
✓ Should be done at last possible moment, after eligibility
criteria has been determined and informed consent has
been obtained
47
 ➢Blinding is a method used to
reduce bias by concealing the
assignment of interventions from
Blinding in one or more parties involved in
RCTs: the trial.
 1. Open-label

The main 2. Single

types: 3. Double
4. Triple
 The main type of blinding…
1. An open-label trial is a type of clinical trial in which
both the researchers and participants know which
treatment is being administered.
2. Single-blind trial
✓In a single-blind trial, the researcher knows the details of
the treatment but the patient does not.
✓Because the patient does not know which treatment is
being administered (the new treatment or another
treatment) there should be no placebo effect.
50
 The main type of blinding…
3. Double-blind trial
▪ In a double-blind trial, one researcher allocates a
series of numbers to 'new treatment' or 'old
treatment’.
➢ The second researcher is told the numbers, but not
what they have been allocated to.
▪ Double-blind describes an especially stringent way
of conducting an experiment, usually on human
subjects, in an attempt to eliminate subjective bias
on the part of both experimental subjects and the
experimenters.
51
 The main type of blinding…
4. Triple-blind trial
✓ The most common meaning is that the subject,
researcher and person administering the treatment
are blinded to what is being given.
✓ Alternately, it may mean that the patient, researcher
and statistician are blinded.
✓ These additional precautions are often in place with
the more commonly accepted term "double blind
trials", and thus the term "triple-blinded" is
infrequently used.
52
Single vs. double vs. triple blind?
▪Much confusion in the use of the terms
single, double, and triple blind, hence the
study should describe exactly who was
blinded.
▪Ideally, blinding should occur at all of the
following levels:
➢Patients
➢Caregivers
➢Data collectors
➢Adjudicators of outcomes
➢Statisticians
53
 • Reduces Bias: Blinding minimizes
various types of bias, including
performance bias (differences in care
provided) and detection bias
(differences in outcome assessment).
Purpose • Enhances Validity: By reducing bias,
and blinding helps to enhance the internal
Benefits of validity of the trial, making the results
more reliable.
Blinding:
• Improves Objectivity: It ensures that
the treatment effects are not
influenced by the placebo effect or by
researchers' preconceptions.
 • Feasibility: In some trials,
especially those involving complex
interventions like surgery or
different modes of physical
therapy, blinding may be difficult
Challenges or impossible to implement.
in • Ethical Considerations: In certain
Blinding: cases, it may be unethical to
withhold treatment information
from participants, especially if
knowing about the treatment
could affect their health decisions.
 ▪Placebos: Using placebos that
resemble the active
treatment can help in blinding
participants.
Implemen ▪For instance, in drug trials,
ting placebos are often used to
Blinding: mimic the appearance, taste,
and administration route of
the active drug.
 • Sham Procedures: In trials
involving surgical or procedural
interventions, sham procedures
can be used to blind participants,
although this raises ethical
Impleme considerations.

nting • Blinded Assessment: Ensuring that

outcome assessors are blinded can
Blinding… help reduce detection bias, even if
the participants and treating
clinicians are aware of the
treatment assignments.
 How is randomization achieved?

▪Two steps involved:

➢ Generation of allocation sequence
➢Implementation of allocation (concealment of
allocation)
➢While both are important, there is evidence
that concealment of allocation is more critical

58
 Generation of allocation sequence:
❖Restricted randomization:
▪ Blocking
▪ Done to ensure equal balance of arms throughout all portions
of the study
▪ For example, blocks of six would have 3 active/3 control
▪ Block size itself can/should vary
❖Stratified randomization
▪ Individuals are identified based on important covariates (sex, age,
etc.) and then randomization occurs within the strata
❖Dynamic or adaptive methods (not common)
59
Dynamic adaptive randomization:
▪Takes into account the participants already
randomized
▪Adjusts the probability boundary based on this
information
▪Takes into account overall balance, stratification level
balance and stratum balance simultaneously
▪Can accommodate various allocation ratios and
number of treatment groups

60
 ▪The dynamic adaptive sampling
method is a sophisticated
approach used in various
research fields, including
clinical trials, ecological studies,
Dynamic
and social science research.
adaptive…
▪This method involves adjusting
the sampling strategy based on
interim results or ongoing data
collection.
 [Link]: The sampling strategy
evolves based on real-time data. This
allows researchers to allocate resources
more efficiently and focus on the most
informative parts of the population.
[Link]: The method is flexible and
Key can be tailored to specific research
features : goals, populations, and changing
conditions during the study period.
[Link]: By continuously refining the
sampling process, the dynamic adaptive
method aims to maximize the
information gained while minimizing
costs and effort.
 [Link] Trials: In adaptive clinical trials,
interim analyses may lead to modifications
in the trial design, such as changing the
sample size, altering the randomization
ratio, or dropping less effective treatment
arms.

[Link] Studies: Researchers might start

with a broad sampling of an ecosystem and
Applications: then focus more intensively on areas
showing the most significant changes or
variations.

[Link] Sciences: Surveys might begin with a

wide sample and then adapt to focus on
subgroups displaying interesting trends or
unexpected responses.
 1. Initial Planning: Define the initial
sampling strategy and criteria for
adaptation. This includes determining
the objectives, population, and initial
sample size.

Steps 2. Data Collection: Collect initial data

using the predefined sampling
involved: strategy.

3. Interim Analysis: Periodically analyze

the collected data to identify patterns,
trends, and areas needing more
detailed investigation.
 4. Adjust Sampling Strategy: Based
on the interim analysis, adjust the
sampling strategy. This could
involve increasing the sample size
Steps in certain areas, changing the
sampling method, or reallocating
involved resources.
… 5. Repeat: Continue collecting data
and performing interim analyses,
refining the sampling strategy
until the study objectives are met.
 1. Improved Accuracy: By focusing on
the most informative data, the
method can improve the accuracy
and relevance of the findings.
2. Resource Optimization: Resources
are allocated more efficiently,
Advantages: potentially reducing the overall cost
and duration of the study.
3. Real-Time Decision Making:
Researchers can make informed
decisions based on real-time data,
improving the study's
responsiveness to new information.
 [Link]: The method requires
sophisticated statistical tools and
expertise to implement and manage
effectively.
[Link] Risk: Without careful planning,
adaptive sampling could introduce
biases, particularly if the criteria for
Challenges: adaptation are not well-defined or are
influenced by external factors.
[Link] Approval: In clinical trials,
adaptive designs may require
additional regulatory scrutiny and
approval due to their complexity and
potential impact on the validity of the
results.
 ▪ A practical example in clinical trials is an
adaptive dose-finding study.
▪ Initially, several doses of a drug may be
tested on a small group of participants.
▪ Based on the interim results, doses that
are less effective or have adverse
Example: effects might be dropped, and the
sample size for more promising doses
might be increased.
▪ This approach ensures that the trial
focuses on the most promising
treatments while minimizing exposure
to ineffective or harmful doses.
 Allocation concealment:

▪Allocation concealment is the mechanism used to

assure that the produced randomization lists and
consequently the treatment to be assigned to the
recruited participants cannot be known or predicted
by all involved parties.
▪The objective of allocation concealment is to reduce
selection bias and it always possible to be
implemented.

69
 Allocation concealment…
▪ Allocation concealed: the authors were deemed to have
taken adequate measures to conceal allocation to study
group assignments from those responsible for assessing
patients for entry in the trial;

▪ Allocation not concealed: the authors were deemed not to

have taken adequate measures to conceal allocation to study
group assignments from those responsible for assessing
patients for entry in the trial.

▪ Unclear allocation concealment: the authors did not report

or provide us with a description of an allocation concealment
approach that allowed for classification as concealed or not
concealed.
70
 Eligibility and Enrollment:
Eligibility is predefined to:
▪ Ensure that participants meet the criteria for the
intervention (e.g., have a specific disease for a
therapeutic trial, are free of disease for a preventive
trial etc.)
▪ Usually eligibility is also defined by age, gender, race,
state of health (absence of contraindications etc.)
▪ The narrower the eligibility criteria, the less
generalizable will be the results
▪ Participants must consent to screening for eligibility.
71
 Enrollment:
Enrollment occurs after:
▪Eligibility is established
▪Consent is provided after an explanation of:
✓All study procedures
✓Risk and benefits
✓Measures to reduce risk
✓Voluntary participation (i.e., can refuse in part or in
whole, or withdraw at any time)
✓Compensation for injury
✓Compensation for time and effort (e.g., money/gifts)
72
 Follow up:

▪Follow up is conducted at predetermined intervals

needed to detect the occurrence of trial endpoints

▪The frequency and duration of follow up will depend

on:
➢Type of endpoint (e.g., response to treatment, development
of new disease, progression of disease, behavioral change,
sustainability of change)

➢The level of risk (higher the risk, more frequent the follow up)
73
 Loss to follow up:

▪Losses to follow-up (LFU) must be minimized b/c:

▪ Losses are often selective (e.g., high-risk persons
drop out of trials) and this introduces bias

▪ Losses to follow-up should be comparable in the

intervention and control arms

▪ Losses to follow-up reduce study power by

reducing the person-time of observation

74
Analyses:
▪Intent-to-treat
▪ Analyze all persons randomized, even if some do not
receive the intervention or drop out before completion of
treatment.
▪ Least biased and most conservative
▪As treated (“per protocol”)
▪ Analyze only those who actually complete the treatment
▪ Potentially biased by selection of the most compliant and
often lowest risk population

75
 Statistical methods:
▪ Outcomes at fixed points in time
▪ Proportion with outcome at each follow-up
▪ Logistic or log-binomial regression
▪ Odds ratio (OR) or prevalence rate ratio (PRR)
intervention/control
▪ Events in-person time
▪ Rate of outcomes per 100 person-years
▪ Poisson regression, incidence rate ratio (IRR) intervention/control
▪ Time-to-event
▪ Time from enrollment until outcome
▪ Cox proportional hazard regression, hazards ratio (HR)
▪ Kaplan-Meier survival analyses, log-rank test
76
 Stopping rules:

❖Trials should have predefined stopping rules to avoid:

▪ Preventing undue risk to participants (e.g., treatment causes
adverse effects)

▪ Depriving the control group of an effective intervention

▪ Continuing an ineffective intervention (“futility” or
conditional power analysis)

77
 Requirements for modification or
termination of an ongoing trial:

▪Observation of a sustained statistical association

that is so extreme, and, therefore, so highly
significant, that it is virtually impossible to arise by
chance alone.

78
 Requirements for modification…

Consider the observed association in the context of

totality of evidence:
▪Are there known or postulated biologic mechanisms
that might explain the observed effect?
▪Is it in-line with other randomized trials, or those from
observational studies?
▪How does the observed association (effect) affect the
risk-to-benefit ratio of the intervention.
79
 Trial Monitoring
▪ Trials must be approved by and monitored by Institutional Review
Boards (IRBs) for ethics and safety
▪ Trials should have an independent monitoring system to periodically
review data and ensure participant safety
▪ Data monitoring committee (DMC) or Data Safety and Monitoring
Board (DSMB)
▪ The DMC or DSMB should have the authority to terminate or change
the trial procedures
▪ Trials should report all adverse events, especially serious adverse
events, and unexpected events
▪ Complex regulations (Good Clinical Practice, GCP)
80
 Ethical challenges of c-RCTS
▪ Individuals in a community may be taking part in a CCRT without
even realizing it, especially if they are in the control arm (i.e.
subject to no new intervention).

▪ Hence, one of the biggest ethical challenges with CCRTs is to

define and to decide who is and who is not a research
participant.

▪ The very nature of a CCRT means that, sometimes, literally tens

of thousands of people may be directly or indirectly involved or
affected by the public health intervention under investigation.

81
 Ethical challenges of c-RCTS …
▪Identifying all of these individuals as ‘research
participants’ to whom the conventional ethical norms
and standards of clinical research trials are applied, may
well mean that the CCRT is no longer either logistically or
financially feasible.
▪Thus RECs have to balance the aims and objectives of the
study carefully (and the importance thereof, in a public
health context) with the need to protect
the rights and interests of individuals and community
members.
82
 Ethical challenges of c-RCTS …
▪The notion of ‘informed consent’ within the context
of a CCRT is particularly challenging, as some form of
‘consent’ should be sought at several levels:
▪Gatekeeper or guardian consent: refers to the entity
that ‘delivers the community’, namely that gives
permission for researchers to undertake the research
in the selected community.
▪Often the ‘gatekeeper’ is the government and/or the
local health authority.

83
 Ethical challenges of c-RCTS …
▪Community consent or engagement: The notion of
‘community consent’ is a misleading one, which is best
avoided.

▪True community consent can only be obtained from

communities that are governed or led by a recognized
political or tribal authority, which is usually not the case.

▪Rather, researchers should discuss in detail, in their REC

applications, the proposed community engagement process,
identifying both successes and challenges.
84
 Ethical challenges of c-RCTS …

▪Elder consent: In certain research contexts, for

example rural villages, consent may need to be
obtained from the recognized village or tribal
‘elder’.
▪Once this consent has been obtained, care must
still be taken to obtain individual consent and to
ensure the voluntariness of individual
participation.

85
 Ethical challenges of c-RCTS …
▪Household consent: Many CCRTs involve accessing
households.
▪This presents several ethical challenges as it may be
unclear as to what defines ‘a household’, as well
as whom is entitled to consent to household access.
▪(Is ‘the household’ those living under one roof, or on
one property, or eating out of one pot, or family
members?
▪Does the concept of ‘the household’ also include any
lodgers?)

86
 Ethical challenges of c-RCTS …
▪ Individual consent: Even after all the above consents
have been obtained, as appropriate, obtaining individual
consent from those identified as ‘research participants’ is
still mandatory.

▪ Often, one of the biggest ethical challenges in a CCRT is

how best to define clearly who qualifies as a ‘research
participant’.

87
Sample size estimates for Individually
randomized trials

▪Most endpoints are measured as events in

person time
▪ Need to estimate person years (py) required to
detect a specified rate in intervention vs
control

▪ Estimate sample size at enrollment and

assumed loss to follow up to provide the
person years needed
88
 Sample size estimates…

▪Specify type I and II error (e.g., power >80% to

detect a difference significant at p < 0.05)

▪Specify an expected or meaningful difference in

outcomes rates b/n intervention and control arms

▪Estimate losses to follow up which reduce person years

▪Estimate required sample size at enrollment using
conventional formula
89
Sample Size in Cluster randomized trials
▪Cluster randomized trials increase sample size
requirements due to intra-cluster correlation.
▪Design effect (D) is the increase in sample size over
individual randomization required to compensate for
intra-cluster correlation (estimated by intra-cluster
correlation coefficient or coefficient of variation).
▪To reduce sample size requirements try to select
▪ More homogeneous clusters (less variability)
▪ Larger cluster populations (lower coefficient of variation) 90
Efficiency in cluster randomization

▪Efficiency is increased with homogeneous population

clusters
▪ Efficiency increased by:
▪ matching
▪ stratified or blocked randomization

▪Larger population per cluster (reduces ICC or K)

▪There is a tradeoff between the number of
clusters and the size of population per cluster

91
 ▪A situation in which the
investigator lacks full control
over the allocation and/or
timing of intervention but
nonetheless conducts the study
Quasi as if it were an experiment,
experimental allocating subjects to groups.
design:
▪Inability to allocate subjects
randomly is a common situation
that may be best described as a
quasi-experiment.
 Quasi-experimental study designs…
▪Quasi-experiments aim to demonstrate causality
between an intervention and an outcome.
▪Quasi-experimental studies can use both pre-
intervention and post-intervention measurements as
well as non-randomly selected control groups;
▪A quasi-experimental design DOES NOT permit the
researcher to control the assignment of participants to
conditions or groups.

93
 Why QUASI-EXPERIMENTS?

▪Because either we cannot randomly allocate

participants to treatment conditions for practical
reasons or
▪it would be unethical to do so (e.g. if it would mean
withholding treatment from someone who needs it).

94
 Types of Quasi-Experimental Designs

1. Nonequivalent Control Group Designs—research

designs having both experimental and control
groups but the participants are NOT randomly
assigned to these groups.
▪ Problems with this type of design have to do with
how to compare the results between groups
when they are not equivalent to begin with.
95
 Types of Quasi-Ex’tal Designs …
Pretest–posttest alternative treatment comparison
design
▪A study wherein one group of clients is assessed,
receives an intervention, and is reassessed.
▪Their results are compared to a comparable group of
clients who were assessed, who then receive an
alternative treatment (e.g., treatment as usual, placebo
care), and are then reassessed.
▪It is an attempt to control various threats to internal
validity, such as passage of time, concurrent history,
regression to the mean, placebo influences, and
expectancy bias.
96
Types of Quasi-Ex’tal Designs …
2. Designs Without Control Groups
a. Interrupted Time-Series Designs—these designs
allow the same group to be compared over time by
considering the trend of the data before and after the
treatment.

97
 Types of Quasi-Ex’tal Designs …

Pretest–posttest no-treatment control group design

▪A study wherein one group of clients is assessed,
receives an intervention, and is reassessed.
▪Their results are compared to a comparable group of
clients who were assessed, not treated, and
then reassessed.
▪It is an attempt to control various threats to internal
validity, such as passage of time, concurrent history, and
regression to the mean.
98
 Types of Quasi-Ex’tal Designs …
▪Comparative Time Series Design
➢Examines two or more variables over time in
order to understand how changes in one variable
are related to changes in another variable

➢Provides indirect evidence that the change in one

variable may be causing the change in the other
variable

99
 Types of Quasi-Ex’tal Designs …

b. Repeated Treatment Designs: this research

design allows the same group to be compared by
measuring participants' responses before and
after repeated treatments.

100
 Types of Quasi-Ex’tal Designs …
▪Longitudinal Designs:
➢The quasi-independent variable is time; nothing
has occurred from one observation to the next
except for the passage of time
➢Mostly used by developmental psychologists to
study age-related changes in how people think, feel,
and behave.
➢Developmental changes in memory, emotions, self-
esteem, personality, etc.

101
Types of Quasi-Ex’tal Designs …

Longitudinal Designs drawback:

▪Difficult to obtain participants who agree to be
in the study over a long period of time;
▪Difficult to keep track of participants once they
are in the study;
▪Repeatedly testing a sample requires time,
effort, and money.

102
 Types of Quasi-Ex’tal Designs …
Cross-sectional Designs drawback:
Age is confounded with generation.
▪Examples:
▪Texting ability by age (10, 20, 30, 40, 50, and 60 year old
persons)
▪ Younger people are faster texting
▪ Does texting speed decrease with age?
▪ Or are there generational effects
▪ with experience with texting?

103
Threats to Internal Validity of RCT:
1. Ambiguous temporal precedence: Lack of
clarity about whether intervention occurred
before outcome;
2. Selection: Systematic differences over
conditions in respondent characteristics that
could also cause the observed effect;
3. History: Events occurring concurrently with
intervention could cause the observed effect;
4. Maturation: Naturally occurring changes over
time could be confused with a treatment effect;
104
 Threats to Internal Validity…
5. Regression to the mean: When units are selected for their extreme
scores, they will often have less extreme subsequent scores, an
occurrence that can be confused with an intervention effect;
6. Attrition: Loss of respondents can produce artifactual effects if that
loss is correlated with intervention;
7. Testing: Exposure to a test can affect scores on subsequent
exposures to that test;
8. Instrumentation: The nature of a measurement may change over
time or conditions;
9. Interactive effects: The impact of an intervention may depend on
the level of another intervention

105
Points to consider while designing:

▪Pick an event or set of events & one DV variable

▪Is it longitudinal, cross-sectional, time-series,
pre-post test, or post-test?
▪Is a non-equivalent control group or reversal included?
▪What is your hypothesis (prediction)?
▪What confounds threaten internal validity?
▪Can you improve the design to address the confounds?
106
Your questions/reflections?