21/11/2024

Dr Md Maruf Haque Khan, PhD

Lecture-9

F A CILITA TOR:
DR M D M A R UF HA QUE KHA N
EXPERIMENTAL STUDIES M BBS, M PH, M SC, PHD
ASSISTAN T PRO F E SSO R

(Materials for this presentation are borrowed from various online sources solely for knowledge dissemination purpose)

1
Dr Md Maruf Haque Khan, PhD

RECAP

❑ Case-control study:
➢ Case
➢ Control ❑ Cohort Study:
➢ Analysis ➢ Cohort
➢ Advantages ➢ Types
➢ Limitation ➢ Analysis
➢ Advantages
➢ Limitation

1
 21/11/2024
Dr Md Maruf Haque Khan, PhD

Experimental Study
Randomization
Randomization Control Trial
Type of Randomizations
Blinding
CONTENTS:
Interventions
Clinical Trial
Quasi-Experimental study
Field Trial
Community Trial

3
Dr Md Maruf Haque Khan, PhD

STUDY TYPES

2
 21/11/2024
Dr M Maruf H Khan MBBS, MPH, MSc, PhD

Epidemiological Study Designs

Observational Experimental

Descriptive Analytical

Case Report Randomized Control

Ecological Study
Trial (RCT)
Case Series Cross-sectional
study Quasi-experimental
Ecological Study
Case-Control Field Trial
Cross-sectional study
study/survey Community Trial
Cohort

5
Dr Md Maruf Haque Khan, PhD

EXPERIMENTAL STUDIES
Experimental studies are a type of research in which investigators
intentionally introduced a treatment/ procedure/ program to observe
the effect on outcomes.
Purpose: To establish causal relationships between variables.
Characteristics:
➢Intervention by the researcher
➢Control over variables
➢Comparison between intervention and control groups

3
 21/11/2024
Dr Md Maruf Haque Khan, PhD

EXPERIMENTAL STUDIES

Significance: Essential for testing hypotheses and evaluating the

effectiveness of interventions.

Fields of Application: Medicine, psychology, public health,

education, and social sciences.

Goal: To provide robust evidence on the efficacy or impact of an

intervention.

7
Dr Md Maruf Haque Khan, PhD

EXPERIMENTAL STUDY

The main difference

Historically, in 1747, In modern usage it is between observational
James Lind first often called as and experimental study
performed the “Randomized is that it is
experimental study Controlled Trial” under direct control of
the investigator

4
 21/11/2024
Dr Md Maruf Haque Khan, PhD

• In 1747 James Lind conducted his

classic experiments aboard the
Salisbury, in which he cured
scurvy with oranges and lemons.
• He took 12 men suffering from
similar symptoms of scurvy,
divided them into six pairs and
treated them
• 42 years later that the Admiralty
first issued an order for the
distribution of lemon juice to sailors

9
Dr Md Maruf Haque Khan, PhD

EXPERIMENTAL STUDIES: TYPES

Major types of experimental studies:

➢Randomized Controlled Trials (RCTs)
➢Quasi-Experimental Studies
➢Community Trials
➢Field Trials

10

5
 21/11/2024
Dr Md Maruf Haque Khan, PhD

EXPERIMENTAL STUDY

• It may describe as prospective, longitudinal, follow-up,

and experimental
• Intervention intentionally introduced by the
investigators
✓Take baseline measure on all groups
✓Give different interventions
✓Measure outcome

11
Dr Md Maruf Haque Khan, PhD

KEY ELEMENTS OF
EXPERIMENTAL
STUDIES

Intervention

Randomization

Blinding

12

6
 21/11/2024
Dr Md Maruf Haque Khan, PhD

Intervention

13
Dr Md Maruf Haque Khan, PhD

An intervention is an action or treatment

applied to participants in a study to evaluate
its effects on specific outcomes.

Purpose: To test the efficacy or effectiveness

of a treatment, procedure, or program on
targeted health outcomes.
INTERVENTION/
MANIPULATION
Importance in Experimental Studies:
• Provides direct evidence of causality
between the intervention and outcomes.
• Enables assessment of the real-world impact
of treatments or programs.

14

7
 21/11/2024
Dr Md Maruf Haque Khan, PhD

TYPES OF I N T E R V E N T I O N
➢ Behavioral: Lifestyle changes (e.g., diet, exercise programs)
➢ Pharmacological: Medication trials (e.g., new drug
treatments)
➢ Surgical/Procedural: Testing new surgical techniques or
medical procedures
➢ Educational: Health education or counseling programs
Etc.

15
Dr Md Maruf Haque Khan, PhD

RANDOMIZATION

16

8
 21/11/2024
Dr Md Maruf Haque Khan, PhD

R A N D O M I Z AT I O N

Randomization is the process of randomly assigning participants to

different groups (e.g., intervention and control) to ensure each
participant has an equal chance of being placed in any group.

Purpose: To reduce selection bias and achieve comparable groups,

helping ensure that any observed effects are due to the intervention,
not external factors.

17
Dr Md Maruf Haque Khan, PhD

RANDOM SAMPLING VS RANDOMIZATION

❑ Random sampling
Each individual in the population has an equal chance of
being selected for the sample. This ensures that the
sample represents the broader population.
❑ Randomization
Once selected for the sample, each person has an equal
chance of being placed into either the experimental or
control group. This means they are randomly assigned to
one of the groups, balancing characteristics across
groups and helping to control for bias.

18

9
 21/11/2024
Dr Md Maruf Haque Khan, PhD

TYPES OF RANDOMIZATION

19
Dr Md Maruf Haque Khan, PhD

TYPES OF
RANDOMIZATION

❖ Simple
randomization
❖ Stratified
randomization
❖ Block
randomization
❖ Cluster
Randomization

20

10
 21/11/2024

Dr Md Maruf Haque Khan, PhD

SIMPLE RANDOMIZATION
➢Each participant has an equal chance of being assigned
to any group, often using a random number generator.
➢Randomization based on a single sequence of random
assignments is known as simple randomization.

Common methods include:

▪ Coin Toss
▪ Envelope
▪ Computer assisted
▪ According to date of birth (odd or even years)
▪ The number of their hospital records
▪ The date at which they are invited to participate in the
study (odd or even days)

21
Dr Md Maruf Haque Khan, PhD

SIMPLE RANDOMIZATION

Patient Treatment
1 A
2 A
3 B
4 A
5 A
6 B
7 B
8 B

22

11
 21/11/2024
Dr Md Maruf Haque Khan, PhD

STRATIFIED RANDOMIZATION

❑Stratified randomization is a method

of sampling which first stratifies the whole
study population into subgroups with
same attributes or characteristics, known as strata

❑Then followed by simple random sampling from the

stratified groups, where each element within the
same subgroup are selected unbiasedly during any
stage of the sampling process, randomly and
entirely by chance.

23
Dr Md Maruf Haque Khan, PhD

STRATIFIED RANDOMIZATION
Patient Treatment
➢If Stratified 1 A

according to the 2 A

Age (<55 and >55) 3 B

4 A
5 A
6 B
7 B
8 B

24

12
 21/11/2024
Dr Md Maruf Haque Khan, PhD

STRATIFIED RANDOMIZATION

25
Dr Md Maruf Haque Khan, PhD

Block randomization
❑ Block randomization works by
randomizing participants within
blocks such that an equal number
are assigned to each treatment.

❑ Block randomization is a common

method used to reduce the
likelihood of bias and have the
same number of participants for
every condition group.

❑ This is especially useful if the

sample size is small.

26

13
 21/11/2024
Dr Md Maruf Haque Khan, PhD

CLUSTER
R A N D O M I Z AT I O N
• Groups or clusters (e.g., schools,
communities) are randomly assigned
instead of individual participants,
often used in public health research.

27
Dr Md Maruf Haque Khan, PhD

RANDOMIZATION: IMPORTANCE

➢ Randomizations prevents selection biases

➢ Randomizations allows comparability.
➢ Balances Confounding Variables
➢ Supports Causal Inference
➢ Enhances Study Validity

28

14
 21/11/2024
Dr Md Maruf Haque Khan, PhD

BLINDING

29
Dr Md Maruf Haque Khan, PhD

BLINDING
• Blinding represents an important, distinct
aspect of randomized controlled trial.
• Term blinding refers to keeping trial
participants, investigators, or accessors
unaware of an assigned intervention, so
that they are not influenced.
• Blinding prevent bias at several stages of
trial

30

15
 21/11/2024

BLINDING: TYPES
➢Un-blinded or open labeled: Everyone knows the
intervention
➢Single-blind or single-masked:
Participants don’t know whether they are taking intervention
Dr Md Maruf Haque Khan, PhD

or placebo
➢Double blind or double-masked :
Neither the person administering the intervention, nor the
individuals know who received what
➢Triple blind or triple-masked :
Although rarely implemented, triple-blind studies occur when
group assignment is hidden not only from participants and
administrators, but also from those tasked with analyzing the
data after the experiment has concluded.
31
Dr Md Maruf Haque Khan, PhD

Source: [Link]

32

16
 21/11/2024
Dr Md Maruf Haque Khan, PhD

RANDOMIZED
CONTROLLED
TRIAL (RCT)

33
Dr Md Maruf Haque Khan, PhD

RANDOMIZED CONTROLLED
TRIALS (RCTS)
➢ A randomized controlled trial (study) Is the gold standard of all
studies
➢ Considered the “gold standard” for testing the effectiveness of
interventions.
➢ Participants are randomly assigned to either the intervention or
control group.
➢ Reduces bias and provides strong evidence for causal
relationships.

34

17
 21/11/2024
Dr Md Maruf Haque Khan, PhD

RANDOMIZED RCT is a trial in which subjects are randomly

CONTROLLED assigned to two groups:
TRIAL (RCT): [Link] experimental group
[Link] comparison group or control

35
Dr Md Maruf Haque Khan, PhD

EXPERIMENTAL GROUP
➢ The Experimental Group in a Randomized Controlled Trial (RCT)
refers to the group of participants that receives the intervention or
treatment being tested.
➢ The experimental group allows researchers to observe the direct
impact of the intervention and establish whether it produces a
statistically significant effect compared to the control group.
➢ This setup is essential for determining causation in scientific
research

36

18
 21/11/2024
Dr Md Maruf Haque Khan, PhD

CONTROL GROUP
Every experiment should have a “control group.”
Types of Control Groups:
► No Treatment Control: Observes outcomes without intervention.
►Placebo Control: Uses an inactive substance that mimics the
intervention.
► Standard Treatment Control: Compares the intervention with the
current standard treatment.

37
Dr Md Maruf Haque Khan, PhD

RANDOMIZED CONTROLLED TRIAL: RCT

Time course

Treatment A
Specify a sample
follow up
population

Study Ascertain whether a

Randomized, disease/outcome of interest
Participants
And assign occurred

follow up
Often, Placebo or
“standard treatment”

Treatment B

38

19
 21/11/2024
Dr Md Maruf Haque Khan, PhD

STEPS OF A RANDOMIZED
CONTROLLED TRIAL (RCT)

39
Dr Md Maruf Haque Khan, PhD

STEPS OF A RANDOMIZED
CONTROLLED TRIAL (RCT)

1) Define the Research Question and Hypothesis

2) Design the Study Protocol
3) Obtain Ethical Approval
4) Recruit Participants
5) Randomize Participants
6) Blinding (if applicable)

40

20
 21/11/2024
Dr Md Maruf Haque Khan, PhD

STEPS OF A RANDOMIZED
CONTROLLED TRIAL (RCT)

7) Administer the Intervention

8) Follow-up and Data Collection
9) Analyze Data
10)Interpret Results
11) Report and Publish Results
12)Post-Trial Follow-up (if applicable)

41
Dr Md Maruf Haque Khan, PhD

STEPS OF A RANDOMIZED
CONTROLLED TRIAL (RCT)

1) Define the Research Question and Hypothesis

Formulate a clear hypothesis regarding the intervention’s
expected effect on the outcome.

2) Design the Study Protocol

Outline all aspects of the study, including objectives, methods,
inclusion/exclusion criteria, intervention details, and outcome
measures.
➢Determine the sample size needed to detect a statistically
significant effect and analysis plan

42

21
 21/11/2024
Dr Md Maruf Haque Khan, PhD

STEPS OF A RANDOMIZED
CONTROLLED TRIAL (RCT)

3) Obtain Ethical Approval

Submit the study protocol to an ethics review board to ensure the
study meets ethical standards and protects participant rights.

4) Recruit Participants
Identify and enroll participants who meet the inclusion criteria
and agree to participate in the study.
➢ Screen for eligibility to ensure participants match the study’s
requirements.

43
Dr Md Maruf Haque Khan, PhD

STEPS OF A RANDOMIZED
CONTROLLED TRIAL (RCT)

5) Randomize Participants
Randomly assign participants to either the experimental
(intervention) group or the control group to reduce selection bias.

6) Blinding (if applicable)

Implement blinding procedures to minimize bias.

44

22
 21/11/2024
Dr Md Maruf Haque Khan, PhD

STEPS OF A RANDOMIZED
CONTROLLED TRIAL (RCT)
7) Administer the Intervention
Deliver the intervention to the experimental group as outlined in
the protocol, while the control group may receive a placebo or
standard treatment.
➢Ensure consistency in how the intervention is administered.

8) Follow-Up and Data Collection

Monitor participants at pre-determined intervals to gather data
on primary and secondary outcomes.
➢Track adherence to the intervention, adverse events, and other
relevant data.

45
Dr Md Maruf Haque Khan, PhD

STEPS OF A RANDOMIZED
CONTROLLED TRIAL (RCT)
9) Analyze Data
Use statistical methods to compare outcomes between the
experimental and control groups.
➢Calculate the effect size to assess whether there is a significant
difference between groups.
10) Interpret Results
Assess the findings in the context of the study’s limitations and
potential confounding factors.
➢Determine whether the results support or refute the hypothesis.

46

23
 21/11/2024
Dr Md Maruf Haque Khan, PhD

STEPS OF A RANDOMIZED
CONTROLLED TRIAL (RCT)

11) Report and Publish Results

Share findings in a clear, transparent manner to allow replication and
evaluation by other researchers.

47
Dr Md Maruf Haque Khan, PhD

DESIGN OF RCT
Reference or target population

Study Population

Sample population

Intervention Group Control Group

Loss of follow-up Loss of follow-up

Outcome Outcome
Assessment Assessment

Compare

48

24
 21/11/2024
Dr Md Maruf Haque Khan, PhD

ST R E N GT H S A N D
L I M I TAT I O N S

49
Dr Md Maruf Haque Khan, PhD

STRENGTHS OF RCT
✓Strongest Evidence for Causation: RCTs are the gold standard
for establishing causal relationships due to random assignment
and control groups.
✓Reduced Bias: Randomization and blinding help minimize
selection, performance, and detection biases, leading to
more reliable results.
✓Control Over Confounding Variables: Random assignment
distributes confounding variables evenly across groups.
✓High Internal Validity: RCTs are rigorously designed to control
for extraneous variables, allowing accurate attribution of
outcomes to the intervention.

50

25
 21/11/2024
Dr Md Maruf Haque Khan, PhD

LIMITATIONS
➢ Costly
➢ Time-consuming
➢ Ethical concerns: withholding an intervention
from a control group or using placebos can
raise ethical concerns, especially in medical
research
➢ Loss of follow up
➢ Contamination of Intervention group
➢ Problem with blinding
➢ External validity

51
Dr Md Maruf Haque Khan, PhD

QUASI EXPERIMENTAL STUDY

52

26
 21/11/2024
Dr Md Maruf Haque Khan, PhD

QUASI EXPERIMENTAL STUDY

▪ Quasi meaning “resembling,” “having some, but not all of the
features of,” partly; pretending to be
▪ Like a true experiment, a quasi-experimental design aims to
establish a cause-and-effect relationship between
an independent and dependent variable.
▪ However, unlike a true experiment, a quasi-experiment does not
rely on random assignment.
▪ Quasi-experimental design is a useful tool in situations where true
experiments cannot be used for ethical or practical reasons

53
Dr Md Maruf Haque Khan, PhD

CHARACTERISTICS OF QUASI -
E X P E R I M E N TA L S T U D I E S
• No Randomization: Participants are not randomly assigned to
groups.
• Comparison Groups: Often includes a control or comparison group.
• Pretest-Posttest: Measures outcomes before and after the
intervention.
• Real-World Settings: Typically conducted in natural environments
like schools or communities.

54

27
 21/11/2024
Dr Md Maruf Haque Khan, PhD

STRENGTHS
AND
LIMITATION

55
Dr Md Maruf Haque Khan, PhD

STRENGTHS:
QUASI-EXPERIMENTAL STUDIES

➢ Ethical Flexibility: Suitable when randomization isn’t feasible.

➢ Real-World Applicability: Findings are relevant to practical settings.
➢ Cost-Effective: Less resource-intensive than RCTs.

56

28
 21/11/2024
Dr Md Maruf Haque Khan, PhD

LIMITATIONS:
QUASI-EXPERIMENTAL STUDIES

➢ Higher Risk of Bias: Without randomization, more vulnerable to bias.

➢ Confounding Variables: Difficult to control for other influencing
factors.
➢ Weaker Causal Inference: Provides less robust causal conclusions
than RCTs.

57
Dr Md Maruf Haque Khan, PhD

QUASI-EXPERIMENTAL STUDIES

Quasi-experimental studies provide valuable insights when RCTs

are not feasible but require careful interpretation due to limitations
in causal inference.

58

29
 21/11/2024
Dr Md Maruf Haque Khan, PhD

FIELD TRIAL

59
Dr Md Maruf Haque Khan, PhD

FIELD TRIALS

Field trials are epidemiological studies conducted in natural real-

world settings to evaluate the effectiveness of interventions.

Purpose: To evaluate new preventive or therapeutic interventions like

vaccines, educational programs, or public health measures on a
large scale.

60

30
 21/11/2024
Dr Md Maruf Haque Khan, PhD

KEY CHARACTERISTICS OF FIELD

TRIALS
• Real-World Setting: Field trials are conducted in natural environments outside
laboratories, such as communities or public areas, rather than in controlled
experimental settings.
• Large Sample Size: These trials usually involve large populations who are at risk for
the studied outcome, aiming to assess the intervention’s impact at a community
level.
• Preventive Focus: Field trials are often used to evaluate preventive measures, like
vaccination programs or health education campaigns.
• Randomization and Control Group: Typically, they incorporate randomization and
include a control group to provide a clear comparison of intervention effects.

61
Dr Md Maruf Haque Khan, PhD

TYPES OF FIELD TRIALS

❑ Preventive Field Trials: Evaluate interventions aimed at
preventing diseases (e.g., vaccination trials).
❑ Therapeutic Field Trials: Focus on treatments and are usually
conducted among individuals who already have a disease.
❑ Community Trials: Interventions are applied at the community
level rather than to individual participants.

62

31
 21/11/2024
Dr Md Maruf Haque Khan, PhD

ST RE N GT H S
AND
L I M I TAT I O N S

63
Dr Md Maruf Haque Khan, PhD

ST R E N GT H S O F F I E L D T R I A L S

• High external validity due to real-world setting.

• Allows testing on a large scale, providing insights into public health
interventions.
• Findings are often more applicable to broader populations.
• Allows assessment of effectiveness, rather than just efficacy.

64

32
 21/11/2024
Dr Md Maruf Haque Khan, PhD

L I M I TAT I O N S O F F I E L D T R I A L S
• Managing and coordinating interventions in real-world settings can be
challenging.
• Field trials often require substantial funding, personnel, and other
resources.
• Ensuring informed consent and participant safety in natural settings poses
additional ethical challenges.
• Controlling for all external influences and biases is harder in real-world
conditions.

65
Dr Md Maruf Haque Khan, PhD

COMMUNITY
TRIAL

66

33
 21/11/2024
Dr Md Maruf Haque Khan, PhD

COMMUNITY TRIAL

•Community trials are large-scale epidemiological studies where

entire communities, rather than individuals, are the unit of
intervention and analysis.

•Purpose: To evaluate the effectiveness of public health

interventions at the community level.

67
Dr Md Maruf Haque Khan, PhD

K E Y F E AT U R E S O F C O M M U N I T Y
TRIALS
❑ Unit of Study: The community, not individuals.
❑ Intervention: Applied at the community level (e.g., villages,
schools, workplaces).
❑ Outcome Measurement: Health outcomes are measured
collectively.
❑ Comparative Design: Often involves a comparison between
intervention and control communities.

68

34
 21/11/2024
Dr Md Maruf Haque Khan, PhD

TYPES OF COMMUNITY TRIALS

❑ Preventive Trials: Focus on interventions like vaccination

campaigns, health education, or water sanitation.
❑ Therapeutic Trials: Evaluate treatment programs (e.g., mental
health services, chronic disease management).
❑ Behavioral Trials: Test the effectiveness of behavior change
strategies (e.g., smoking cessation, dietary changes).

69
Dr Md Maruf Haque Khan, PhD

ST R E N GT H S O F CO M M U N I TY
TRIALS

➢ High External Validity: Results are more generalizable to the

broader population.
➢ Population-Level Impact: Evaluates interventions that target
groups or entire communities.
➢ Real-World Settings: Conducted in natural environments,
reflecting practical implementation.

70

35
 21/11/2024
Dr Md Maruf Haque Khan, PhD

L I M I TAT I O N S O F C O M M U N I T Y
TRIALS

• Logistical Complexity: Requires significant resources and

coordination.
• Ethical Challenges: Informed consent and balancing risks and
benefits at the community level.
• Potential for Contamination: Interventions in one community may
influence nearby control communities.
• Confounding Factors: Difficult to control all external variables.

71
Dr Md Maruf Haque Khan, PhD

COMMUNITY TRIALS

➢ Community trials are critical for evaluating the real-world impact

of public health interventions.
➢They provide valuable insights for improving population health
and guiding policy decisions.

72

36
 21/11/2024
Dr Md Maruf Haque Khan, PhD

CLINICAL TRIAL
73
Dr Md Maruf Haque Khan, PhD

CLINICAL TRIAL

• A clinical trial is a type of experimental study

designed to evaluate the safety, efficacy,
and/or effectiveness of medical, surgical,
behavioral, or other healthcare interventions
in humans.
• It is a systematic, prospective investigation
conducted with the goal of answering specific
research questions related to the prevention,
diagnosis, treatment, or management of
diseases.

74

37
 21/11/2024
Dr Md Maruf Haque Khan, PhD

CLINICAL TRIAL PHASES

➢Phase I studies usually test new drugs for the first

time in a small group of people to evaluate a
safe dosage range and identify side effects.

➢Phase II studies test treatments that have been

found to be safe in phase I but now need a
larger group of human subjects to monitor for any
adverse effects.

Source: [Link]

75
Dr Md Maruf Haque Khan, PhD

CLINICAL TRIAL PHASES

➢Phase III studies are conducted on larger

populations and in different regions and countries
and are often the step right before a new
treatment is approved.
➢Phase IV studies take place after country
approval and there is a need for further testing in
a wide population over a longer timeframe.

Source: [Link]

76

38
 21/11/2024
Dr Md Maruf Haque Khan, PhD

CLINICAL TRIAL PHASES

Approximate Number
Phase of people taking part Main aims of trial Randomization
Phase I 20–100 healthy volunteers Assess safety and No
determine dose range

Phase II 100 – 300 volunteers Assesses efficacy and Usually

further evaluates safety

Phase III Hundreds or Confirm safety and Mostly

thousands of people efficacy on a larger scale

Phase IV Large population Study long-term benefits No

and monitor side effects

77
Dr Md Maruf Haque Khan, PhD

[Link]

78

39
 21/11/2024
Dr Md Maruf Haque Khan, PhD

EVIDENCE
HIERARCHY IN
EPIDEMIOLOGI
CAL STUDY

79
Dr Md Maruf Haque Khan, PhD

E v i d e n c e
Hierarchy in Exp.
Studies
Epidemiolog
ical Studies
Cohort study

Case-control study

Cros-sectional study

Ecological Study

Case series

Case Report

80

40
 41
21/11/2024

QUESTION
Dr Md Maruf Haque Khan, PhD Dr Md Maruf Haque Khan, PhD

81

82
 21/11/2024
Dr Md Maruf Haque Khan, PhD

ASSIGNMENTS

1) Define experimental studies and List the major types of

experimental studies
2) What are the key differences between observational and
experimental studies?
3) Explain the role of randomization in RCTs.
4) List and briefly describe the different types of randomization.
5) What is blinding, and why is it important in RCTs? List the
different types of blinding.
6) Compare the strengths and limitations of RCTs.
7) Describe the characteristics of Quasi-Experimental Studies

83
Dr Md Maruf Haque Khan, PhD

THANK YOU

84

42