Scribd
Upload
30 views28 pages

Desain Study - SDA 1

This document discusses and compares different epidemiological study designs, including randomized controlled trials (RCTs), cross-sectional studies, case-control studies, and cohort studies. It provides details on the characteristics, strengths, and limitations of experimental and observational study designs. Experimental designs like RCTs allow for control of confounding factors through randomization and blinding but have limitations related to generalizability and ethics. Observational designs are more practical for rare diseases and allow investigation of multiple outcomes, though they cannot prove causality and are subject to biases. The choice of study design depends on the research question, disease characteristics, and feasibility considerations.

Uploaded by

oneng ifayani
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
30 views28 pages

Desain Study - SDA 1

This document discusses and compares different epidemiological study designs, including randomized controlled trials (RCTs), cross-sectional studies, case-control studies, and cohort studies. It provides details on the characteristics, strengths, and limitations of experimental and observational study designs. Experimental designs like RCTs allow for control of confounding factors through randomization and blinding but have limitations related to generalizability and ethics. Observational designs are more practical for rare diseases and allow investigation of multiple outcomes, though they cannot prove causality and are subject to biases. The choice of study design depends on the research question, disease characteristics, and feasibility considerations.

Uploaded by

oneng ifayani
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
You are on page 1/ 28

STUDY DESIGNS:

RCT, CROSS SECTIONAL,


CASE-CONTROL, COHORT

Sofa Dewi Alfian


2021
STUDY DESIGNS

• Theoretical design
(research question)

• Design of data collection

• Design of statistical
analysis
Choice of study design
Ø There are several designs for data collection with pros and
cons;
Ø Choice of design:
• Dependent on the research question;
• Nature of disease (acute vs chronic)
• Type of exposure (medication use): duration (hours to years),
frequency (constant or temporal), strength (low vs high dose)
• Feasibility (staff, time, costs, study population, etc.)
• Ethical aspects.
Epidemiologic Studies

Experimental Studies Observational Studies

Clinical Trials (RCTs) Descriptive Studies

Community Intervention Trials


Case-Control Studies
Field Trials
Cohort Studies
Design of data collection

1. Experimental
• Assignment of the intervention by researcher.

2. Observational
• No assignment of determinant by researcher,
but rather by mechanisms of routine practice.
1. Experimental studies
Clinical trials: Interventions assigned to patients.

Characteristics:
• Experiment (Trial)
• Double/triple blind
• Randomized
• Controlled
Response on
therapy/intervention depend on:

Subjectivity of the
patient and/or
Natural course (A)
health care
professional (SPH)

Pharmacological/
External effect (EE) intervention effect
(IE)
Natural course of disease
Control the study
• Placebo/known drug

Randomization
• Goal: to get comparable groups
SUBJECTIVITY EXTERNAL EFFECTS
Blinded (double/triple) Control/blinded
• Both patient and health care • Placebo effect
professional (researcher) do • Induced external effect
not know to which group a
patient was appointed vChange in life style
(intervention or control)
Effect of therapy/intervention

- Response intervention group (Ri) = NCi + SPHi + EEi + IEi


- Response control group (Rc) = NCc + SPHc + EEc + IEc

Natural course of disease: à comparable as a result of


randomisation
Subjectivity of evaluation: à comparable as a result of blinding

Effect of therapy: Ri – Rc = IEi - IEc


Example:
Experimental design

STRENGTHS LIMITATIONS

• Randomization controls for • Generalizability


confounding, selection bias, • Prolonged duration
and confounding by • Ethical issue
indication.
• Blinding controls for
information bias
2. OBSERVATIONAL STUDIES

Descriptive studies: distribution of exposure


and outcome.
• Develop potential hypothesis (hypothesis
generating), confounding plays no role in
descriptive studies

Analytical studies: determination of a relation


between exposure and outcome.
• Test hypotheses that were previously
developed (hypothesis testing)
Descriptive studies

DESCRIPTIVE STUDY: CROSS SECTIONAL

Participants are sampled


independent of exposure and
outcome, and prevalence of
exposure and outcome are
assessed at the same point in time.
Example:
CROSS SECTIONAL

Strength Limitation
• Establish • Can not establish
prevalence temporal
relationship (what
was first?
exposure or
disease?)
Analytical study: COHORT
Exp: antacids during pregnancy and asthma in
Participants identified children
based on exposures and 100 97
pregnant
followed over time for the women Normal
incidence of outcomes. children
.
Free of outcome/
disease at the time of
starting exposition.
Measure of association:
3 asthma
RR
Two types of cohort:

Closed Subjects enter the cohort at one point in time

cohort Fixed membership, no one can be added or excluded

Exp: Citizens of Japan who were exposed to radiation on


Hiroshima and Nagasaki bombing

Open Subjects are allowed to enter at different points in time


(dynamic)
cohort Members can leave or be added over time

Exp: Subjects are continually added when they are


diagnosed with cancer. Subjects can also leave the
cohort by moving or dying
Example:
Flowchart of numbers of non-persistent and non-adherent
patients over three years.
COHORT

Strengths Limitations
• Clearly determine • Validity can be influence by
sequence of exposure and lost to follow up
outcome • Not suitable when the
• Can study multiple outcome is rare
outcomes from an exposure • Prolonged duration
• Can measure incidence • Dependent on the data in
(risk) of outcome an existing data set (some
• Relatively inexpensive relevant information may
(retrospective: existing not detailed enough)
database)
Analytical study: Case control
Cases and controls are Mother Child

sampled based on the


outcome of interest, and the
Asthma
prevalence of exposure in
these two groups is then
compared.
No asthma

Measure of association:
Odds ratio
Example:
CASE CONTROL

Strengths Limitations
• Useful for rare/long • Bias in measurement
latency periods of of exposure (recall
outcomes bias)
• Time efficient • Limited to one
• Can study multiple risk outcome variable
factors for a single
disease
COHORT VS CASE CONTROL STUDY
Case-control study
Exposure Disease
?
?
Prospective cohort study
Exposure Disease
?
?

Retrospective cohort study


Exposure Disease
?
?
= present basis on which group are ? = to bedetermined
= absent selected at beginning of study = investigator at beginning of study
Points to discuss
1. Research question
2. Study design and why they choose the study design
3. Data sources and why they choose the sources
4. Limitations of the data source
THANK YOU!
[email protected]

You might also like