Study types

Module 3
Study Types/Designs
1

Module 3- Study types/designs
Learning Objectives
At the end of this section, you will be able to:
 Describe the common types of study designs used in
HSR.
 Mention the advantages and limitations of each type of
study design
 Identify the most appropriate study design for the
research proposal you are developing.
2

Study types or study designs
 The type of study chosen depends on:
 The type of problem;
 The knowledge already available about the problem;
and
 The resources available for the study.
 Study designs broadly can be classified as
interventional or non interventional studies.
3

Study design….
Table: Classification of research study designs
4
I. Non-interventional (observational) studies
 Exploratory Qualitative
 Ecological (correlational) population as
study unit
Descriptive
Studies
Epidemiologicalstudy
designs(Quantitative)
 Case reports
 Case series
 Cross-sectional surveys
individualas
studyunit
 Cross-sectional comparative study
 Case control
 Cohort
Analytical
Studies
II. Interventional studies
 Experimental studies (Randomized)
 Quasi-experimental studies (Not Randomized)

Study designs…
An EXPLORATORY STUDY is
 a small-scale study of relatively short duration,
 carried out when little is known about a situation or a
problem.
 It may include description as well as comparison.
 It may include description as well as comparison.
For example:
 Description: To explore needs of HIV positive and AIDS
patients, a number of in-depth interviews can be held with
various categories of patients (males, females, married, single)
and with some counselors working on a program that is already
under way.
5

Exploratory study…
 Comparison: To identify variables that help to
explain why one group of persons or objects
differs from another.
 To explain the differences we observe (e.g., in the
needs of male and female AIDS patients) or to
identify causes of problems.
 Note: If the problem and its contributing factors
are not well defined, it is always advisable to do
an exploratory study before embarking on a
large-scale descriptive or comparative study.
6

7
Study designs….
EPIDEMIOLOGICAL STUDIES: Purpose
Descriptive studies Analytic studies
Characterize disease
occurrence by time, place
and person.
Generate testable
hypothesis as to the cause
of disease
Concerned with the
search for causes and effects.
Test hypothesis about
association between
exposure and outcome.

Study designs…
10
Descriptive studies
A. Dealing with individuals
- Case report/case study
- Case series
- Cross sectional surveys (usually)
B. Dealing with population
- Correlational or ecological(some times)

Case Report/case study
11
 Careful and detailed report of the profile of a single
patient by one or more clinicians
• Document unusual medical occurrences
• Can generate hypothesis, provide clues in
identification of a new disease or adverse effects of
exposures
 (E.g. It was a single case report that formulated the
hypothesis of oral contraceptive use increases venous
thromboembolism)
 It is made using
 Simple history, physical examination and Lab./ radiologic

Case Series Studies
12
 Description of clinical/epidemiologic characteristics of
a number of patients (usually 5-12) with a given
disease having similar diagnosis
• Collection of individual case reports occurring within
a fairly short period of time
 Used as an early means to identify the beginning or
presence of an epidemic, generate hypothesis and
gives information about natural history of disease
 Can suggest the emergence of a new disease (i.e.
PCP …. AIDS)

Example of case-series studies
 Five young, previously healthy homosexual men
were diagnosed as having PCP at Los Angeles
hospital during a six month period from 1980 to 1981
 This form of pneumonia had been seen almost
exclusively among older men and women whose
immune systems were suppressed
 This unusual circumstance suggested that these
individuals were actually suffering with a previously
unknown disease, subsequently it was called AIDS
13

Uses of case series studies
 Can be valuable early evidence for associations
between exposures and diseases which can be
studied in more detail
 Useful for the recognition of new diseases,
 Useful for constructing of the natural history of a
disease,
 Use to formulate a hypothesis and to detect an
epidemic
14

Cont….
15
Limitations of case report and series studies :
• No appropriate comparison group
• Based on the experience of one person so
Can’t be used to test for presence of a valid
statistical association …prone to atomistic
fallacy
 not a true epidemiologic design

Cross-sectional study
16
 Measure disease and exposure status simultaneously
among individuals in a well-defined population at a
point in time …..also called a “prevalence
study/survey”)
 Snapshot of the health status of populations at a
certain point in time

Cont…
17
 Can have descriptive or analytic purposes
 The descriptive type is carried out to study prevalence
of health related events at a point in time/snapshot
 Diseases, risk factors, coverage of interventions,
health service utilization, knowledge, attitude and
practice
 The analytic type is carried out to assess association
between exposure and outcome
 Exposure and disease status are assessed
simultaneously among individuals at the same point in
time
 Compare prevalence of disease in persons with and
without the exposure of interest

18
Cross-Sectional Studies….
Steps in the conduct of cross-sectional studies:
1. Define a population of interest (reference or source
population)
2. Recruiting a representative sample (adequate size,
random selection)
3. Measure the variables of interest (disease &or exposure)
at the same point in time
4. Analyze the data

20
Example:
Respiratory problems
Yes no total
Smoking Yes 70 50 120
no 30 70 100
Total 100 120 220
Prevalence of smokers (among respiratory problems)
=70 x100=70%
100
Prevalence of respiratory problems (among smokers)
=70 x100=58.3%
120

21
Examples…
 General household surveys
 National Health and Nutrition Examination
Survey
 International surveys (International Study of
Asthma and Allergies in Childhood (ISAAC)

Cross-sectional Study….
22
Advantage:
 helps to determine prevalence …disease burden
 Fast/Inexpensive - no waiting!
 No loss to follow up
 multiple factors and outcomes at same point in time
can be studied
 Helps to generate hypotheses

Cross-sectional study….
23
Disadvantage
 Cannot determine causality
 Temporal sequence between exposure and
disease can’t be established, i.e. which came
first, chicken or the egg?

Ecologic Studies
24
 A study in which one or more exposures or disease
is measured at the population level rather than the
individual level
 Uses data from entire population to compare
disease frequencies (average values)
- between different groups during the same
period of time, or
- in the same population at different points in time.
 Correlation coefficient (r) is the measure of
association

Examples of correlational studies
1. Trend of HIV in Ethiopia
 HIV prevalence of Ethiopia at different years or points in
time
2. Geographic distribution of HIV in the regions of Ethiopia
 HIV prevalence of different regions of Ethiopia at the
same year or point in time
3. Fluoride content of water and dental caries (correlation)
 Proportion of people with dental caries in villages
Vs
 Fluoride content of water in villages during the same
period or point in time
25

Breast Cancer Mortality and Dietary Fat
Intake
26
Ecologic correlation of breast cancer mortality
and dietary fat intake

Ecologic Studies…
27
Limitation
 Lack of ability to control for effects of potential
confounding factors.
 Inability to link exposure with disease at
individual level
 association found with aggregate data (average
values) may not apply to individuals (Prone to
ecological fallacy)
 Measurement limitation (Ecological conditions are
difficult to measure at individual level)
 E.g environmental contact, fluoride content of water

Ecological fallacy: example
28
 Imagine a study of the rate of coronary heart disease in
the capital cities of the world relating the rate to average
income.
 Within the cities studied, coronary heart disease is
higher in the richer cities than in the poorer ones.
 We might predict from such a finding that being rich
increases your risk of heart disease, but
 In the industrialised world the opposite is the case -
within cities such as London, Washington and
Stockholm, poor people have higher CHD rates than rich

Atomistic fallacy
29
 Studies of individuals, case report and case series study,
are prone to the opposite of the ecological fallacy, the so-
called atomistic fallacy.
 Wrongly assuming from observations on the causes of
disease in individuals that the same forces apply to whole
populations.
 For example, at an individual level a high income or a marker
of material success such as employment, car access etc., is
associated with a lower rate of suicide. But,
 Does not mean that populations or societies which are rich
have a lower rate of suicide or better mental health, rather
the opposite seems to be true.

30
Study designs…
Assignment
of exposure by researcher
yes no
Random allocation
to comparison gps
yes No
Experiment e.g
Randomized
Clinical trial
Quasi- experiment
yes
no
Comparison
Descriptive Case-control cohort
ObservationalInterventional

ANALYTIC STUDIES
31
 Focuses on identifying determinants of a disease by
testing the hypothesis formulated from descriptive
studies
 the ultimate goal is judging whether a particular
exposure causes or prevents disease (unwanted health
related event)
 Analytic studies are broadly classified into two -
observational and interventional studies.
 Both types use "control group", the use of control group
(comparison grp) is the main distinguishing feature of
analytic studies.
In Observational, information is obtained by observation
of events.
 No intervention is done, no deliberate interference with
natural course of disease. (cross-sectional, case control,

Cont…
32
In Interventional study, the researcher does something
about the exposure and observes the changes on the
outcome or disease.
 Investigator has control over who gets exposure and
who don't.
 The key is that the investigator assign study participants
into either group, whether it is done randomly(RCT,
Experimental) or not randomly (quasi-experimental).

33
Cohort Studies
 Cohort
 a group of people who share a common experience or
condition
 E.g. Birth cohorts, cohort of smokers, occupational exposures
 Cohort studies
 The observation of a cohort over time to measure outcome(s)
 Because the data on exposure and disease refer to different
points in time, cohort studies are longitudinal
 Longitudinal, follow-up or incidence studies

34
Cont…
 They have 2 primary purposes:
 Descriptive: to describe the incidence rates of
an outcome
 Analytic: to analyze associations between the
outcomes and risk factors (Usual type)

35
Cont…
 begin with a group of people free of disease
 who are classified into subgroups according to
exposure to a potential cause of outcome
 and the whole cohort is followed up to see how
the subsequent development of outcome
differs between the groups with and without
exposure (Figure below)

36
Figure 1- design of cohort study

37
Types of Cohort Studies
 Closed vs. Open
 Closed cohort: exposure groups are defined at the
start of follow-up and no new members are added
during the follow-up
 Open/dynamic cohort: people move in and out the
study

38
Cont…
 Incidence cohort vs. Prognostic (clinical)
 Incidence Cohort Study
To assess incidence of disease
To identify risk factors for disease onset
Incidence greater in exposed than non-exposed?

Cont…
39
 Prognostic Cohort Study
Follow diseased cohort to assess factors
associated with outcome (recovery or death)
Goal is to identify explanatory/prognostic
factors/ factors helped to the dev’t of the out
come of the disease.

40
Cont…
 Prospective vs. Retrospective (Concurrent vs.
Non-concurrent)
 Depending on temporal relationship between
initiation of the study and time of collection of
exposure and outcome data from the study
subjects or participants
 Cohort studies have been called prospective
studies, but this terminology is confusing and should
be avoided
 the term “prospective” refers to the timing of data collection
and not to the relationship between exposure and effect
 Thus, there can be both prospective and

41
Prospective cohort studies
 Exposure and outcome data is collected
after start of the study
 cohorts Identified in the present
 exposure status or possible
explanatory/prognostic factors determined in
the present
 Cohorts followed-up to identify outcome
 Ascertainment of outcome done in future

42
2016 2017 2018
Fig. 2. Design of prospective cohort studies

43
Cont…
 Advantages
 Exposure precedes outcome
 Outcome unknown when exposure determined
 Can examine many outcomes of the exposure
 Disadvantages
 Cost
 Time delays
 Loss to followup

44
Retrospective cohort studies
 all the exposure and effect data have been
collected before the actual study begins
 This type of investigation is called a historical
cohort study
 Conduct
 Identify cohort in the past using
records/databases
 Determine exposure or prognostic factors in
the past using again records or databases
then
 Identify outcome in past or present or future
(in case of mixed cohort)

45
Cont…
 Costs can occasionally be reduced by using a historical
cohort (identified on the basis of records of previous
exposure)
 This sort of design is relatively common for studies of
cancer related to occupational exposures
 For example, records of military personnel exposure to
radioactive fall-out at nuclear bomb testing sites have
been used to examine the possible causal role of fall-out
in the development of cancer over the past 30 years

46
2013 2014 2015
Fig. 3. Design of retrospective cohort studies

47
Cont…
 Advantages:
 Do not require a very long time (exposures and/or
outcomes have already occurred)
 Cheap, if used record linked for outcomes
 Disadvantages:
 Feasible only when a list of exposed individuals is
available
 Exposure data often of poor quality
 Usually unable to measure confounders

48
Design and data collection of
cohort study (1)
1. Define and identify cohorts
1.1. Identify population at risk
 Selection of Exposed Population
 Depends on research question
 Depends on frequency of exposure
 Common exposures: general population
 Rare exposures: selected groups

49
Design and data collection (2)
 Outcome must not be rare in exposed
 Attributable risk must be high
 Accessible and compliant subjects
 E.g., Nurse’s Health Study, Physicians
 Selection of Non-exposed Group
 Similar to exposed
 Control for confounding factors

50
Design and data collection (3)
1.2. Screen identified subjects for the disease and
omit the prevalent cases
2. Define, assess, identify and classify exposure
3. Follow-up and ascertain outcome
 Timing of outcome events-case definition

51
Sampling
Sample size - for test of significant difference between two
proportions, the following formula can be used:
Parameters:
n - size of sample in each group
P1 ,P2–estimated population prevalence in the comparison
groups
β = 1- Power (the probability that if the two proportions
differ the test will produce a significant difference)
 Usually a power of 80% is used
      
 2
21
2211
2
2 11
pp
ppppZZ
n


 

52
Analysis
(statistically prospective cohorts are summarized using RR but retrospective
by OR)
 RR=incidence exp/inc non exp
 Presence of association
 Population
 RR=1 – no association; RR<1 – negative association;
RR>1 – positive association
 Sample
 P-value<0.05 – statistically significant association
 RR≠1
 Statistical methods – survival analysis
 Strength of association
 Weak – RR close to 1; Strong – RR far from 1

Case control study
Design concept
 Starts with cases and comparative group(control)
 We determine what proportion of cases were exposed
and what proportion were not
 We also determine what proportion of controls were
exposed and what proportion were not
 Also called case-referent or retrospective
53

Case-control….cont
Study pop
cases
controls
exposed
Not exposed
Not exposed
exposed
Study begins here
54

Designing case control studies
I. Selection of cases (definition, eligibility criteria)
 Hospitals, other medical care facilities/general population
II. Selection of controls (definition, eligibility criteria)
 General population, neighborhood, friends/relatives,
hospital or clinic-based
***The benefit of increased sample size is not as relevant
past the 1:4 ratio (e.g. increase in statistical power).
III. Ascertaining Exposure
 Sources of exposure data (cases and controls)
***The measure of association in case control study is Odds
Ratio(OR)
55

Advantages of Case-Control Studies
 Quick and easy to complete, cost
effective
 Most efficient design for rare diseases
 Usually requires a smaller study
population than a cohort study
56

 Uncertainty of exposure-disease time
relationship
 Inability to provide a direct estimate of risk
 Not efficient for studying rare exposures
 Subject to biases (recall & selection bias)
Disadvantages of Case-Control
Studies57

INTERVENTION STUDIES
58
 Investigator determines who is exposed, ideally
using random methods
 Investigator allocates the exposure and follows
for an outcome
 Types of interventional studies include
 Randomized Clinical Trials
 Field Trials
 Community Intervention Trials
 Quasi-experimental Studies

What is an experimental study?
60
 Randomized controlled trials are sub-types of
cohort studies in which exposure (i.e.,
treatment) is randomly assigned by the
investigator (or by some other, observable
phenomenon)
 Have a long history in clinical medicine
 Although experimental studies come in many
types, principles are the same and clinical
trials dominate the field

What is a clinical trial?
61
 A clinical trial is a prospective study evaluating
the effect and value of intervention(s) in
human beings under pre-specified conditions.
 A controlled clinical trial is a prospective study
comparing the effect and value of
intervention(s) against a control in human
beings.

62
 The clinical trial is the most definitive tool for
evaluation of the applicability of clinical
research.
 It represents a key research activity with the
potential to improve the quality of health care
and control costs through careful comparison
of alternative treatments.

When might a RCT be
indicated?63
 Exposure is a modifiable factor which persons will let you
modify, e.g., taking a pill, trying a different diet
 When there is ethical equipoise, that is when we really do
not know whether a particular exposure is associated with
benefit or with harm- Imperative that informed
consent be obtained
 A particular exposure may have an influence on multiple
outcomes of tremendous importance
 In experimental trials, in contrast with other epidemiologic
study designs we have discussed, we are doing something
to participants so we have to be certain that, first, we do no
harm

Clinical Trial Phases
64
 Phase I: clinical pharmacology and toxicity
 Phase II: Initial Assessment of Efficacy
 Phase III: Full-scale Evaluation of Treatment
Efficacy
 Phase IV: Postmarketing Surveillance

Phases…65
Phase I: clinical pharmacology and
toxicity
 1st experiment in human for new drug, schedule,
or combination
 Primary concern: Safety
 Goal: define the maximum tolerated dose (MTD)
in a dose-escalation study
 Typically required 15-30 patients

Phases…
66
 Phase II
 Small randomized, controlled, blinded
 Tests tolerability and different doses
 E.g., optimal dosage without side effects
 Applied to patients with relevant illness
 Goal - Identify suitable formulation of drug

Intervention Trials
67
 Phase III
 Referred to as clinical trial
 Evaluation of efficacy of drug
 Usually randomized, blinded, controlled trial
 If successful, licensed and marketed
 Phase IV
 Large studies after approval of drug
 Often observational, study long-term effects
 Long term efficacy, rate of serious side effects
 Evaluate drug in “real life”, additional uses

Conducting Trials
68
1. Selecting participants
2. Measure baseline characteristics and describe
sample
3. Randomizing
4. Apply intervention
5. Follow-up and adherence to protocol
6. Measuring outcome
7. Analysis

1. Selection of Participants
69
 Terminology
 Target population
 People to which findings will be generalized
 Study population
 Subset of target population available/accessible to
study
 Selecting subjects
 Establish inclusion/exclusion criteria
 Sample size

70
Source population
Study population
Randomize
Treatment No treatment
threats to external validity
threats to
internal validity

71
Population At Large
Population With Condition
Study Population
Study Sample
Define Condition
Entry Criteria
Enrollment

Sample size
72
Calculating sample sizes for trials with
dichotomous outcomes (eg, sick vs well)
requires four components:
 type I error (α),
 power,
 event rate in the treatment group(p1),
 RR or event rate in the control group(p2)
,RR=P1/p2

Participants
74
 Inclusion criteria
 Define main characteristics of target population that
are relevant to research question
 Demographic characteristics
 E.g., adults, aged 20-69
 Clinical characteristics
 E.g., in good health
 Geographic characteristics
 E.g., living in northern Ethiopia
 Temporal characteristics
 E.g., inception period Jan 1, 2003 to Dec 31, 2003

Participants
75
 Exclusion criteria
 Subsets of people meeting inclusion criteria (potentially suitable
for research question) except for characteristics that might
interfere with quality of data etc.
 High likelihood of being lost to follow-up
 E.g., transients
 Inability to provide good data
 E.g., language barrier or cognitive incapacity
 High risk for side effects
 E.g., pregnant, lactating
 Unethical to withhold treatment
 E.g., severe depression

Exclusion Criteria
76
 Five main reasons for exclusion from clinical
trial
 Safety concerns (susceptibility to adverse effects of
active treatment)
 Unethical to withhold treatment (tx so beneficial for
some  not acceptable to assign placebo
 Active treatment unlikely to be effective
 Unlikely to adhere to treatment
 Unlikely to provide outcome information (e.g., die or
move before study completion)

Conducting Trials
77
sample
3. Randomizing
7. Analysis

2. Baseline Characteristics
78
 Need enough information to track subjects
 Contact persons; address, etc.
 Description of participants
 Aid in assessing generalizability (e.g., gender, age,
disease severity, etc.)
 Risk factors for outcome or to define subgroups
 E.g., smoking status, smoking status of spouse
 Measure of “outcome” variable
 E.g., if pain is “outcome”, need baseline pain

Conducting Trials
79
sample
3. Randomizing
7. Analysis

3. Randomization
80
 Should be done at the last possible moment,
after eligibility criteria has been determined
and informed consent has been obtained
 Important to conceal randomization scheme
from attending health care providers

Advantages of Randomization
81
 Removes the potential of bias in the allocation
of participants.
 Prevents confounding
 produce comparison groups

Methods of randomization
82
 Fixed allocation Randomization
 simple Randomization
 Stratified Randomization

Stratified Randomization
83
 Select factor(s) of interest
 Stratify (divide) group by that factor
 Randomize the appropriate proportion of each
group into your treatment groups
 Increases the likelihood that your treatment
groups will be comparable on that factor

Stratified Randomization
84
 E.g., age is important in treatment response
 100 in sample  want 50 per group
 Say 20% of sample are >60 (high risk group)
 Randomly select 10 people over 60 for each
group
 Then randomly select 40 people under 60 for
each group

Conducting Trials
85
sample
3. Randomizing
7. Analysis

4. Applying Intervention
86
 Intervention strategy compared with
 Placebo
 Standard treatment
 May have more than one comparison group
 Advantages, disadvantages of “placebo”?
 Ethical issues
 Advantages, disadvantages of “standard treatment”
control?
 Interpretation of findings?

Blinding
87
 Randomization
 Control for confounding bias at baseline
 Does not control for confounding during follow-up
 E.g., differential attention to subjects in treatment arm
 Does not control for information bias
 Blinding
 Controls for
 Information bias (e.g., observer bias)
 Reduce loss to follow up (reduce selection bias)

88
Blind studies
Single blind The patients do not know
which treatment they receive
Double blind The patient and the observer or
the physician do not know
Triple blind The patient, the observer and
the analyst do not know

Conducting Trials
89
sample
3. Randomizing
7. Analysis

5. Follow-up and Adherence
90
 Ideally
 All subjects adhere to treatment regimens; do not
seek additional treatment; do not drop out, die,
move or have to be withdrawn from study; attend
follow-up sessions and provide outcome data

Unplanned Crossovers
91
 Unplanned crossover is said when subjects
switch to either treatments
 When subjects choose the alternative treatment
 Subjects in experimental group start using
“control” treatment or vice versa
 Usually have selective cross-over (more subject
from one group cross over)
 A large proportion of crossovers may invalidate
study

Conducting Trials
92
sample
3. Randomizing
7. Analysis

6. Measuring Outcome
93
 Outcome should be
 Clinically relevant
 Feasible
 E.g., choose outcome that is sufficiently common for time and
number of subjects
 Able to be measured accurately and precisely
 Not too costly
 Above all, valid, reliable and sensitive to change

Conducting Trials
94
sample
3. Randomizing
7. Analysis

Analysis
95
 Analyze according to which treatment the
patient was randomized to (which treatment was
intended?)
 “intention to treat” analysis
 Or according to which treatment they actually
received?
 “per protocol” analysis

Intention to treat vs. per protocol
analysis96
 Intention to treat analysis (management trial):
 Includes all randomized patients in the
groups to which they were randomly
assigned, regardless of their adherence with
the entry criteria, regardless of the treatment
they actually received, and regardless of
subsequent withdrawal from treatment or
deviation from the protocol

ITT---cont
97
 Key points
 Use every subject who was randomized
according to randomized treatment
assignment
 Ignore noncompliance, protocol deviations,
withdrawal, and anything that happens after
randomization
 As randomized, so analyzed

Intention to treat---cont
98
Advantage
Randomization is preserved
Simulate the real world
Disadvantage:
If many patients switch treatment, difference b/n
groups will be obscured

Per protocol---cont
99
Per protocol analysis:
 Patients who deviate from the protocol are
excluded from the analysis
Advantage: determine efficacy of intervention
Disadvantage: vulnerable to all source of bias

QUASIEXPERMENTAL
STUDIES100
 In these studies, one characteristic of true
experiment (i.e randomization ) is missing.
 But, they always include intervention or
manipulation of the independent variable.
 The common quasi-experimental studies are
described below.
 a)Non-equivalent control group design
 b) Before-After Study design

Non-equivalent control group design
101
 Uses two or more groups (one serves as a control
group)
 The subjects in study (intervention) group and control
group are not randomly assigned.
Figure: Diagram of a quasi-experimental design with two groups

Before-After Study design
102
 Uses only one group in which an intervention is carried
out. The situation is analyzed before and after the
intervention to test if there is any difference in the
observed problem.
 Figure: Diagram of a before-after study

Quasi-experimental studies…
103
 Advantage of quasi-experimental
designs:
 Often more practical than randomized studies.

Study types

More Related Content

What's hot (20)

Viewers also liked (20)

Similar to Study types (20)

More from Fasika Alemu (18)

Recently uploaded (20)

Study types