SlideShare ist ein Scribd-Unternehmen logo
1 von 50
Epidemiological Study Designs:
• Broadly, the epidemiological studies may be
classified in to the following two broad
categories, based on the types of exposure:
1. Observational Study
2. Experimental Study
1
By: Anil Chaudhary (MPH), NOC, Lalitpur,
Nepal.
According to WHO classification:
Observational studies Experimental studies
Descriptive study Clinical trial (RCT)
Analytical study Field trial
Cross sectional study Community trial
Ecological study
Case control study
Cohort study
2
By: Anil Chaudhary (MPH), NOC, Lalitpur,
Nepal.
1. Observational studies: in observational study, the researcher
has no control over the exposure in another word , the
allocation or assignment of factors is not under the control of
investigator; he (she) just observe the situation/event and
records it, which may be descriptive or analytic. The
observational study is also called non-interventional study.
2. Experimental studies: In experimental study, the researcher
has control over the exposure, he doesn’t only observe the
situation and record it, but also manipulate the situation and
measure the effect of manipulation. The experimental study
is also known as interventional study.
3
By: Anil Chaudhary (MPH), NOC, Lalitpur,
Nepal.
Observational studies
Descriptive
- Case report
- Case series
- Ecological
- D. cross-sectional
Analytical
- Cohort
- Case control
- Analytical Cross sectional
- A. Ecological
By: Anil Chaudhary (MPH), NOC, Lalitpur,
Nepal.
Observational Study Designs
4
Descriptive Studies
 Studies that focus on characterizing morbidity or mortality in
populations by person, place or time variables.
 They do not have a priori hypothesis.
 Are not designed to test preconceived suppositions about the
relationships between exposure and outcome.
 Focus is on describing what exists.
By: Anil Chaudhary (MPH), NOC, Lalitpur,
Nepal.
5
Descriptive study types:
1. Case reports
- detailed description of an individual(patient)
2. Case series
- Describes characteristics of a group or cluster of individuals
with the same disease or symptoms.
- Presents a relatively complete profile of case (disease,
illness)
By: Anil Chaudhary (MPH), NOC, Lalitpur,
Nepal.
6
Cont…
3. Ecological Study
- The unit of analysis is group such as countries, states, cities,
hospitals or schools
- Investigator have a summary measure of exposure and a
summary measure of outcome for each group being studied
- Data on exposure and outcome for individual is not
collected.
- Association is identified only at group level.
By: Anil Chaudhary (MPH), NOC, Lalitpur,
Nepal.
7
Cont…
• If we draw conclusion for individual based on
ecological study findings we commit an
ecological fallacy
• Ecological fallacy is an error of reasoning that
one commits when group associations are
used to draw conclusions about associations
at the individual level that may not
necessarily exist.
By: Anil Chaudhary (MPH), NOC, Lalitpur,
Nepal.
8
Types of ecological studies
Exploratory studies
• Descriptive studies that look at variations in
outcomes across ecological units such as
countries, states etc.
• Exposure is not assessed
Multiple- group comparison studies
• Looks for or test associations between average
exposure levels and overall outcome rates.
• Generally based on secondary sources
By: Anil Chaudhary (MPH), NOC, Lalitpur,
Nepal.
9
Cont…
Time – trend studies
Detect changes in the average exposure level and outcome rates
for a single population over time
Mixed studies
Examines changes in average exposure level and outcome rates
for several population over time.
By: Anil Chaudhary (MPH), NOC, Lalitpur,
Nepal.
10
Cont…
4. Cross- sectional study
• One observes a sample of a population at a single point or
brief period of time.
• Exposure and outcome assessed at same time period.
• The unit of analysis is individual
• Also referred as prevalence studies.
• Prevalence rates are the usual measure employed in the
analysis stages.
By: Anil Chaudhary (MPH), NOC, Lalitpur,
Nepal.
11
Cont…
a b
c d
Present (Dis.) Absent (Dis.)
Outcome Status
Exposure Status
Exposed
Unexposed
a+ b
c+ d
a + c b+ d n (a+b+c+d)
Crude Prevelance
rate (PR) =
{(a+c)/n} * 100
PRe =
[a/(a+b)]*100
PRue =
[c/(c+d)]*100
By: Anil Chaudhary (MPH), NOC, Lalitpur,
Nepal.
12
Analytical studies
• Analytical studies are designed to test hypothesis about the
association between an exposure of interest and a particular
outcome.
By: Anil Chaudhary (MPH), NOC, Lalitpur,
Nepal.
13
Case control studies
• Begins by classifying subjects according to their outcome
status.
• Cases of the disease being investigated are selected along
with a comparable group of control who do not have the
outcome in question.
• The cases and controls are then examined for exposure of
interest.
• In case control study one is going from effect to cause.
• Cases and controls are selected and data are collected about
past exposure that may have contributed to disease.
By: Anil Chaudhary (MPH), NOC, Lalitpur,
Nepal.
14
Cont…
 Seeks to identify possible cause of the disease by finding out
how the cases and controls differ.
 Takes into consideration that the case groups must have
been exposed to some factors that contributes to the
causation of their disease.
 Compares the frequency of exposure among cases and
controls
By: Anil Chaudhary (MPH), NOC, Lalitpur,
Nepal.
15
Schematic Diagram of Case Control Study Design
By: Anil Chaudhary (MPH), NOC, Lalitpur,
Nepal.
16
Selection of cases
 First step: Establishing the diagnostic criteria and definition
of disease.
 Incidence (new cases) - preferred
 Prevalence cases are more difficult to link a specific cause
with a disease outcome – because it is influenced by the
development and duration of disease.
By: Anil Chaudhary (MPH), NOC, Lalitpur,
Nepal.
17
Selection of cases
• Sources of cases:
– Records from public health clinics
– Physician offices
– Health maintenance organizations
– Hospitals
– Industrial and government sources.
• Cases should be representative of all persons with the
disease.
By: Anil Chaudhary (MPH), NOC, Lalitpur,
Nepal.
18
Selection of cases
• All persons with the disease may be included in the study.
• However, random selection is required.
• A large random sample from a population of interest ensures
the results can be appropriately generalized.
• Researchers can use restriction (limiting subjects to certain
characteristics) to reduce potential bias and to increase
feasibility.
By: Anil Chaudhary (MPH), NOC, Lalitpur,
Nepal.
19
Selection of controls
• In order to ensure a valid and reliable case-control study, the
controls should look like cases with the exception of not
having the disease.
• Controls should be selected from the same population as the
cases.
• Controls should be representative of general population.
• Controls should have the same probability of being selected
and exposed as the cases.
By: Anil Chaudhary (MPH), NOC, Lalitpur,
Nepal.
20
Selection of controls
• Sources of controls:
– General population as cases
– Same hospital as cases
– Family, friends, or relatives of cases
• In some circumstances, selecting more than one control
group may be useful.
• It may also be useful to select more controls when few cases
are available. This increases power of the study
• The ratio of controls : cases should not exceed 4 : 1.
By: Anil Chaudhary (MPH), NOC, Lalitpur,
Nepal.
21
Exposure Status
• Information about exposure status can be obtained through
– Medical records
– Interviews
– Questionnaires
– Surrogates (such as spouses, siblings, or employers)
• Information on exposure status between cases and controls
should be collected in a similar manner (in order to avoid
bias).
• Blinding interviewers or those assessing medical records to
cases and controls may further minimize bias.By: Anil Chaudhary (MPH), NOC, Lalitpur,
Nepal.
22
Exposure Status
• Preferable to blind those performing the assessment
to the hypothesis of the study (because such
knowledge could influence how they probe or scan
records for information).
By: Anil Chaudhary (MPH), NOC, Lalitpur,
Nepal.
23
Measure of association
• Commonly used measure of the relative
probabilities of disease in case-control studies is
ODDS RATIO (relative odds).
• ODDS RATIO: is appropriate for measuring the
strength of association between exposure and
disease variables.
By: Anil Chaudhary (MPH), NOC, Lalitpur,
Nepal.
24
ODDS RATIO
Cases Controls Total
Exposed a b a + b
Unexposed c d c + d
Total a + c b + d N = a + b + c + d
Odds of exposure among case group = [a/(a+c)]÷ [c/(a+c)] = a/c
Odds of exposure among control group = b/d
Odds Ratio (OR) = (a/c) ÷ (b/d) or ad/bc
Odds of an event can be defined as the ratio of the proportion of cases
exposed to proportion of cases not exposedBy: Anil Chaudhary (MPH), NOC, Lalitpur,
Nepal.
25
ODDS RATIO (OR)
• If the OR = 1, this indicates no association between exposure
and disease.
• If the OR > 1, this indicates a positive association between
exposure and disease.
• If the OR < 1, this indicates a negative association between
exposure and disease.
By: Anil Chaudhary (MPH), NOC, Lalitpur,
Nepal.
26
Cohort study
• A cohort is defined as a population group, or subset thereof (
distinguished by a common characteristics), that is followed
over a period of time.
• Best method for determining the incidence and natural history
of a condition.
• Because data on exposure and disease refer to different points
in time, cohort studies are longitudinal in nature.
• In single cohort studies, those who do not develop the disease
are used as internal controls.
• When two cohorts are used, one group has been exposed or
treated with an agent; and the other group not treated with
agent act as external controls.
By: Anil Chaudhary (MPH), NOC, Lalitpur,
Nepal.
27
Cont…
• Start with a population at risk
• Measure characteristics at baseline
• Follow-up the population over time with surveillance or re-
examination
• Compare events rates in people with and without
characteristics of interest
– Study participants may be either fixed (subjects do not vary
over time and dropouts are not replaced) or dynamic (where
new subjects enter the study in accordance with eligibility
criteria.
By: Anil Chaudhary (MPH), NOC, Lalitpur,
Nepal.
28
Schematic Diagram of Cohort Study Design
By: Anil Chaudhary (MPH), NOC, Lalitpur,
Nepal.
29
Prospective cohort studies (90%)
• The term prospective refers to the timing of data collection
and not to the relationship between exposure and effect.
• In this type of study, a group of people are chosen who do
not have outcome of interest on the basis of exposure and
followed for a long time until the events occur.
• The cohort are then followed longitudinally into the future
to determine if the rate of development of the study outcome
is significantly higher in the exposed group compared to
unexposed group.
By: Anil Chaudhary (MPH), NOC, Lalitpur,
Nepal.
30
Retrospective Cohort (10%)
• Makes us of historical data to determine exposure level at
some base line in the past
• Follow up for subsequent occurrence of disease between
baseline and the present is performed.
• The cohort is considered historical as it represents a group
of people once they were in the past.
• Once cohort has been identified, next step is to classify
subjects by exposure status.
By: Anil Chaudhary (MPH), NOC, Lalitpur,
Nepal.
31
Measure
Disease No disease Total
Exposed a b a + b
Unexposed c d c + d
Total a + c b + d N = a + b + c + d
Relative Risk = Incidence rate in the exposed / Incidence rate in the non exposed
= [a/(a+b)] ÷ [c/(c+d)]
By: Anil Chaudhary (MPH), NOC, Lalitpur,
Nepal.
32
Cont…
• RR = 1 , implies that the risk(rate) of disease
among the exposed is no different from the risk of
disease among the non exposed
• RR>1, implies risk is high among exposed
• RR<1, Implies exposure is not fully associated with
risk of disease
By: Anil Chaudhary (MPH), NOC, Lalitpur,
Nepal.
33
Experimental Study Designs
1. Randomized Control Trials
2. Non Randomized Trials
By: Anil Chaudhary (MPH), NOC, Lalitpur,
Nepal.
34
Randomized Control Trial
• Is an experiment where individual subjects are
randomly assigned to either an experiment or
control group to assess the effects of a preventive or
therapeutic agent, treatment, procedure, or service.
By: Anil Chaudhary (MPH), NOC, Lalitpur,
Nepal.
35
RCT:Can be grouped into 3 categories
1. Preventive Trials
2. Therapeutic trials
3. Intervention trials
By: Anil Chaudhary (MPH), NOC, Lalitpur,
Nepal.
36
Design and analysis of a RCT may be considered
in ten stages:
1. Specification of the program
2. Subject selection
3. The observation
4. Allocation of subject
5. The control group
6. Required no of subjects
7. Control of subjective factors
8. Follow up
9. Outcome
10. analysis
By: Anil Chaudhary (MPH), NOC, Lalitpur,
Nepal.
37
Process
1. Develop the hypothesis
2. Selection of sample
First, Reference population must be specified
Next, identify experimental population
Finally, sample population is determined.
Eligibility criteria( exclusion and inclusion)
By: Anil Chaudhary (MPH), NOC, Lalitpur,
Nepal.
38
3. Allocate subjects into Experimental
and Control groups
Randomization
The subjects have same probability of being
assigned to both group
By: Anil Chaudhary (MPH), NOC, Lalitpur,
Nepal.
39
4. Apply the intervention
- Experimental group exposed to promising but
unproven agent, treatment, procedure or
service
- Control group exposed to either a placebo or
the customary treatment for the problem
By: Anil Chaudhary (MPH), NOC, Lalitpur,
Nepal.
40
5 . Assess the outcome during follow
up
- Subjects are followed up prospectively
- Assessment of outcomes during follow up
may be subject to measurement bias
- Bias can occur when subjects are aware of
which group they have been assigned to
- Placebo effect can occur
By: Anil Chaudhary (MPH), NOC, Lalitpur,
Nepal.
41
Bias can be minimized through blinding
(masking)
- Single blinding: A single blind experiment only the participant
does not know whether they are part of the treatment or
control group,
- Double blinding: A double-blind experiment both the
participant and the experimenter are kept in the dark as to
who is in the treatment and who is in the control group
By: Anil Chaudhary (MPH), NOC, Lalitpur,
Nepal.
42
Randomized Control Trial (RCT):
By: Anil Chaudhary (MPH), NOC, Lalitpur,
Nepal.
43
Other designs of randomized control trials
1. Restricted randomization :
 randomization and comparison is done within strata
2. Sequential analysis :
no. of observation not fixed in advance
Data continuously analyzed
Trial interrupted as soon as a statistical significance is
reached
By: Anil Chaudhary (MPH), NOC, Lalitpur,
Nepal.
44
Cont…
3. Factorial design
• Simultaneous evaluation of two or more treatment
as well as their outcomes
4. Trials on collective units
• Random distribution of group of individuals
By: Anil Chaudhary (MPH), NOC, Lalitpur,
Nepal.
45
Difficulties in application of RCT for
evaluation
- Randomization is not always possible (ethical issues )
- Randomization does not answer the crucial questions,
regarding what is the actual impact
- Comparability resulting from randomization is frequently
partly destroyed (double blinding rarely applicable)
- The randomized comparison of individual components
impossible as evaluation is multidimensional
By: Anil Chaudhary (MPH), NOC, Lalitpur,
Nepal.
46
Non randomized trials
• A study where participants have been assigned to the
treatment, procedure, or intervention alternatives by a
method that is not random. The investigator defines and
manages the alternatives
• It do not meet the criteria for a true experimental design
By: Anil Chaudhary (MPH), NOC, Lalitpur,
Nepal.
47
When is it appropriate to use a non-randomized trial
design?
• When the act of random allocation may reduce the
effectiveness of the intervention
• When it would be unethical to do random allocation
• When it is impractical to do random allocation
 (e.g. cost or convenience factors)
• When there are legal or political obstacles to random
allocation
By: Anil Chaudhary (MPH), NOC, Lalitpur,
Nepal.
48
Various types
- Uncontrolled trials with a single examination after the
intervention
- Before and after comparison
- Controlled non randomized trials
- Non randomized controlled trials based on collective units
By: Anil Chaudhary (MPH), NOC, Lalitpur,
Nepal.
49
By: Anil Chaudhary (MPH), NOC, Lalitpur,
Nepal.
50

Weitere ähnliche Inhalte

Was ist angesagt?

Measures of association 2013
Measures of association 2013Measures of association 2013
Measures of association 2013
dinahoefer11
 
Cross sectional study by Dr Abhishek Kumar
Cross sectional study by Dr Abhishek KumarCross sectional study by Dr Abhishek Kumar
Cross sectional study by Dr Abhishek Kumar
ak07mail
 
Relative and Atribute Risk
Relative and Atribute RiskRelative and Atribute Risk
Relative and Atribute Risk
Tauseef Jawaid
 

Was ist angesagt? (20)

Analytical study designs case control study
Analytical study designs case control studyAnalytical study designs case control study
Analytical study designs case control study
 
What does an odds ratio or relative risk mean?
What does an odds ratio or relative risk mean? What does an odds ratio or relative risk mean?
What does an odds ratio or relative risk mean?
 
4. case control studies
4. case control studies4. case control studies
4. case control studies
 
Measures of association 2013
Measures of association 2013Measures of association 2013
Measures of association 2013
 
Secondary attack rates
Secondary attack ratesSecondary attack rates
Secondary attack rates
 
Biases in epidemiology
Biases in epidemiologyBiases in epidemiology
Biases in epidemiology
 
Case control study
Case control studyCase control study
Case control study
 
ODDS RATIO AND RELATIVE RISK EVALUATION
ODDS RATIO AND RELATIVE RISK EVALUATIONODDS RATIO AND RELATIVE RISK EVALUATION
ODDS RATIO AND RELATIVE RISK EVALUATION
 
Epidemiology lecture3 incidence
Epidemiology lecture3 incidenceEpidemiology lecture3 incidence
Epidemiology lecture3 incidence
 
Odds ratio
Odds ratioOdds ratio
Odds ratio
 
CASE CONTROL STUDY
CASE CONTROL STUDYCASE CONTROL STUDY
CASE CONTROL STUDY
 
Epidemiology Exercises
Epidemiology ExercisesEpidemiology Exercises
Epidemiology Exercises
 
Cross sectional study by Dr Abhishek Kumar
Cross sectional study by Dr Abhishek KumarCross sectional study by Dr Abhishek Kumar
Cross sectional study by Dr Abhishek Kumar
 
3 cross sectional study
3 cross sectional study3 cross sectional study
3 cross sectional study
 
Prevalence and incidence
Prevalence and incidencePrevalence and incidence
Prevalence and incidence
 
Randomized Controlled Trial
Randomized Controlled TrialRandomized Controlled Trial
Randomized Controlled Trial
 
Case control study
Case control studyCase control study
Case control study
 
ANALYTICAL EPIDEMIOLOGY
 ANALYTICAL EPIDEMIOLOGY  ANALYTICAL EPIDEMIOLOGY
ANALYTICAL EPIDEMIOLOGY
 
Relative and Atribute Risk
Relative and Atribute RiskRelative and Atribute Risk
Relative and Atribute Risk
 
Screening in Public Health
Screening in Public HealthScreening in Public Health
Screening in Public Health
 

Andere mochten auch

Epidemiological studies
Epidemiological studiesEpidemiological studies
Epidemiological studies
Bruno Mmassy
 
Overview of Epidemiological Study
Overview of Epidemiological StudyOverview of Epidemiological Study
Overview of Epidemiological Study
Ultraman Taro
 
XNN001 Introductory epidemiological concepts - Study design
XNN001 Introductory epidemiological concepts - Study designXNN001 Introductory epidemiological concepts - Study design
XNN001 Introductory epidemiological concepts - Study design
ramseyr
 
Epidemiological studies
Epidemiological studiesEpidemiological studies
Epidemiological studies
jayarajgr
 
Case control & cohort study
Case control & cohort studyCase control & cohort study
Case control & cohort study
Bhumika Bhatt
 
Validity, its types, measurement & factors.
Validity, its types, measurement & factors.Validity, its types, measurement & factors.
Validity, its types, measurement & factors.
Maheen Iftikhar
 
Presentation Validity & Reliability
Presentation Validity & ReliabilityPresentation Validity & Reliability
Presentation Validity & Reliability
songoten77
 

Andere mochten auch (20)

Epidemiological studies
Epidemiological studiesEpidemiological studies
Epidemiological studies
 
Epidemiological Studies
Epidemiological StudiesEpidemiological Studies
Epidemiological Studies
 
Epidemiological Studies
Epidemiological StudiesEpidemiological Studies
Epidemiological Studies
 
Overview of Epidemiological Study
Overview of Epidemiological StudyOverview of Epidemiological Study
Overview of Epidemiological Study
 
RSS study design
RSS study designRSS study design
RSS study design
 
Epidemiological Studies
Epidemiological StudiesEpidemiological Studies
Epidemiological Studies
 
XNN001 Introductory epidemiological concepts - Study design
XNN001 Introductory epidemiological concepts - Study designXNN001 Introductory epidemiological concepts - Study design
XNN001 Introductory epidemiological concepts - Study design
 
Basic concepts and principles of epidemiology
Basic concepts and  principles of epidemiologyBasic concepts and  principles of epidemiology
Basic concepts and principles of epidemiology
 
Epidemiological studies
Epidemiological studiesEpidemiological studies
Epidemiological studies
 
Epidemiological studies
Epidemiological studiesEpidemiological studies
Epidemiological studies
 
General Epidemiology
General EpidemiologyGeneral Epidemiology
General Epidemiology
 
Cohort Study
Cohort StudyCohort Study
Cohort Study
 
Case Control Studies
Case Control StudiesCase Control Studies
Case Control Studies
 
Case control & cohort study
Case control & cohort studyCase control & cohort study
Case control & cohort study
 
Cohort Study
Cohort StudyCohort Study
Cohort Study
 
Epidemiology
EpidemiologyEpidemiology
Epidemiology
 
Validity, its types, measurement & factors.
Validity, its types, measurement & factors.Validity, its types, measurement & factors.
Validity, its types, measurement & factors.
 
Presentation Validity & Reliability
Presentation Validity & ReliabilityPresentation Validity & Reliability
Presentation Validity & Reliability
 
Epidemiology ppt
Epidemiology pptEpidemiology ppt
Epidemiology ppt
 
Case control studies
Case control studiesCase control studies
Case control studies
 

Ähnlich wie Epidemiological study designs by anil mph

Atoma Research Methodology presentation .pdf
Atoma Research Methodology presentation .pdfAtoma Research Methodology presentation .pdf
Atoma Research Methodology presentation .pdf
MitikuTeka1
 

Ähnlich wie Epidemiological study designs by anil mph (20)

Atoma Research Methodology presentation .pdf
Atoma Research Methodology presentation .pdfAtoma Research Methodology presentation .pdf
Atoma Research Methodology presentation .pdf
 
HLinc presentation: levels of evidence
HLinc presentation:  levels of evidenceHLinc presentation:  levels of evidence
HLinc presentation: levels of evidence
 
randomised controlled trial
randomised controlled trial randomised controlled trial
randomised controlled trial
 
Rerearch design
Rerearch designRerearch design
Rerearch design
 
Reserch methodology
Reserch methodologyReserch methodology
Reserch methodology
 
Research Methodology / Experimental research design
Research Methodology / Experimental research designResearch Methodology / Experimental research design
Research Methodology / Experimental research design
 
HEALTHCARE RESEARCH METHODS: Experimental Studies and Qualitative Studies
HEALTHCARE RESEARCH METHODS: Experimental Studies and Qualitative StudiesHEALTHCARE RESEARCH METHODS: Experimental Studies and Qualitative Studies
HEALTHCARE RESEARCH METHODS: Experimental Studies and Qualitative Studies
 
L5 rm cohort studies case control studies
L5 rm cohort studies case control studiesL5 rm cohort studies case control studies
L5 rm cohort studies case control studies
 
Observational analytical and interventional studies
Observational analytical and interventional studiesObservational analytical and interventional studies
Observational analytical and interventional studies
 
3. Health Research Methods.ppt
3. Health Research Methods.ppt3. Health Research Methods.ppt
3. Health Research Methods.ppt
 
Cohort study
Cohort studyCohort study
Cohort study
 
ANALYTICAL STUDIES.pptx
ANALYTICAL STUDIES.pptxANALYTICAL STUDIES.pptx
ANALYTICAL STUDIES.pptx
 
Types of studies 2016
Types of studies 2016Types of studies 2016
Types of studies 2016
 
Seminar case control study
Seminar case control studySeminar case control study
Seminar case control study
 
5. cohort studies
5. cohort  studies5. cohort  studies
5. cohort studies
 
observational analytical and interventional studies
observational analytical and interventional studiesobservational analytical and interventional studies
observational analytical and interventional studies
 
Research Methods course experimental design
Research Methods course experimental designResearch Methods course experimental design
Research Methods course experimental design
 
BIOSTAT_GROUP-5-Section-7.pptx
BIOSTAT_GROUP-5-Section-7.pptxBIOSTAT_GROUP-5-Section-7.pptx
BIOSTAT_GROUP-5-Section-7.pptx
 
L6 rm experimental design
L6 rm experimental designL6 rm experimental design
L6 rm experimental design
 
Cohort study
Cohort studyCohort study
Cohort study
 

Kürzlich hochgeladen

How to Build a Simple Shopify Website
How to Build a Simple Shopify WebsiteHow to Build a Simple Shopify Website
How to Build a Simple Shopify Website
mark11275
 
Call Girls In Ratnagiri Escorts ☎️8617370543 🔝 💃 Enjoy 24/7 Escort Service En...
Call Girls In Ratnagiri Escorts ☎️8617370543 🔝 💃 Enjoy 24/7 Escort Service En...Call Girls In Ratnagiri Escorts ☎️8617370543 🔝 💃 Enjoy 24/7 Escort Service En...
Call Girls In Ratnagiri Escorts ☎️8617370543 🔝 💃 Enjoy 24/7 Escort Service En...
Nitya salvi
 
怎样办理巴斯大学毕业证(Bath毕业证书)成绩单留信认证
怎样办理巴斯大学毕业证(Bath毕业证书)成绩单留信认证怎样办理巴斯大学毕业证(Bath毕业证书)成绩单留信认证
怎样办理巴斯大学毕业证(Bath毕业证书)成绩单留信认证
eeanqy
 
Minimalist Orange Portfolio by Slidesgo.pptx
Minimalist Orange Portfolio by Slidesgo.pptxMinimalist Orange Portfolio by Slidesgo.pptx
Minimalist Orange Portfolio by Slidesgo.pptx
balqisyamutia
 
一比一定(购)西悉尼大学毕业证(WSU毕业证)成绩单学位证
一比一定(购)西悉尼大学毕业证(WSU毕业证)成绩单学位证一比一定(购)西悉尼大学毕业证(WSU毕业证)成绩单学位证
一比一定(购)西悉尼大学毕业证(WSU毕业证)成绩单学位证
eqaqen
 
Top profile Call Girls In Meerut [ 7014168258 ] Call Me For Genuine Models We...
Top profile Call Girls In Meerut [ 7014168258 ] Call Me For Genuine Models We...Top profile Call Girls In Meerut [ 7014168258 ] Call Me For Genuine Models We...
Top profile Call Girls In Meerut [ 7014168258 ] Call Me For Genuine Models We...
gajnagarg
 
Top profile Call Girls In Sonipat [ 7014168258 ] Call Me For Genuine Models W...
Top profile Call Girls In Sonipat [ 7014168258 ] Call Me For Genuine Models W...Top profile Call Girls In Sonipat [ 7014168258 ] Call Me For Genuine Models W...
Top profile Call Girls In Sonipat [ 7014168258 ] Call Me For Genuine Models W...
nirzagarg
 
Anupama Kundoo Cost Effective detailed ppt with plans and elevations with det...
Anupama Kundoo Cost Effective detailed ppt with plans and elevations with det...Anupama Kundoo Cost Effective detailed ppt with plans and elevations with det...
Anupama Kundoo Cost Effective detailed ppt with plans and elevations with det...
sriharipichandi
 
怎样办理莫纳什大学毕业证(Monash毕业证书)成绩单留信认证
怎样办理莫纳什大学毕业证(Monash毕业证书)成绩单留信认证怎样办理莫纳什大学毕业证(Monash毕业证书)成绩单留信认证
怎样办理莫纳什大学毕业证(Monash毕业证书)成绩单留信认证
ehyxf
 
一比一原版(ANU毕业证书)澳大利亚国立大学毕业证原件一模一样
一比一原版(ANU毕业证书)澳大利亚国立大学毕业证原件一模一样一比一原版(ANU毕业证书)澳大利亚国立大学毕业证原件一模一样
一比一原版(ANU毕业证书)澳大利亚国立大学毕业证原件一模一样
yhavx
 
poliovirus-190801072449. pptx
poliovirus-190801072449.            pptxpoliovirus-190801072449.            pptx
poliovirus-190801072449. pptx
ssuser0ad194
 
一比一定(购)卡尔顿大学毕业证(CU毕业证)成绩单学位证
一比一定(购)卡尔顿大学毕业证(CU毕业证)成绩单学位证一比一定(购)卡尔顿大学毕业证(CU毕业证)成绩单学位证
一比一定(购)卡尔顿大学毕业证(CU毕业证)成绩单学位证
wpkuukw
 
怎样办理伦敦国王学院毕业证(KCL毕业证书)成绩单留信认证
怎样办理伦敦国王学院毕业证(KCL毕业证书)成绩单留信认证怎样办理伦敦国王学院毕业证(KCL毕业证书)成绩单留信认证
怎样办理伦敦国王学院毕业证(KCL毕业证书)成绩单留信认证
eeanqy
 
Top profile Call Girls In Mysore [ 7014168258 ] Call Me For Genuine Models We...
Top profile Call Girls In Mysore [ 7014168258 ] Call Me For Genuine Models We...Top profile Call Girls In Mysore [ 7014168258 ] Call Me For Genuine Models We...
Top profile Call Girls In Mysore [ 7014168258 ] Call Me For Genuine Models We...
gajnagarg
 

Kürzlich hochgeladen (20)

How to Build a Simple Shopify Website
How to Build a Simple Shopify WebsiteHow to Build a Simple Shopify Website
How to Build a Simple Shopify Website
 
Call Girls In Ratnagiri Escorts ☎️8617370543 🔝 💃 Enjoy 24/7 Escort Service En...
Call Girls In Ratnagiri Escorts ☎️8617370543 🔝 💃 Enjoy 24/7 Escort Service En...Call Girls In Ratnagiri Escorts ☎️8617370543 🔝 💃 Enjoy 24/7 Escort Service En...
Call Girls In Ratnagiri Escorts ☎️8617370543 🔝 💃 Enjoy 24/7 Escort Service En...
 
怎样办理巴斯大学毕业证(Bath毕业证书)成绩单留信认证
怎样办理巴斯大学毕业证(Bath毕业证书)成绩单留信认证怎样办理巴斯大学毕业证(Bath毕业证书)成绩单留信认证
怎样办理巴斯大学毕业证(Bath毕业证书)成绩单留信认证
 
Minimalist Orange Portfolio by Slidesgo.pptx
Minimalist Orange Portfolio by Slidesgo.pptxMinimalist Orange Portfolio by Slidesgo.pptx
Minimalist Orange Portfolio by Slidesgo.pptx
 
Just Call Vip call girls Fatehpur Escorts ☎️8617370543 Two shot with one girl...
Just Call Vip call girls Fatehpur Escorts ☎️8617370543 Two shot with one girl...Just Call Vip call girls Fatehpur Escorts ☎️8617370543 Two shot with one girl...
Just Call Vip call girls Fatehpur Escorts ☎️8617370543 Two shot with one girl...
 
一比一定(购)西悉尼大学毕业证(WSU毕业证)成绩单学位证
一比一定(购)西悉尼大学毕业证(WSU毕业证)成绩单学位证一比一定(购)西悉尼大学毕业证(WSU毕业证)成绩单学位证
一比一定(购)西悉尼大学毕业证(WSU毕业证)成绩单学位证
 
How to Create a Productive Workspace Trends and Tips.pdf
How to Create a Productive Workspace Trends and Tips.pdfHow to Create a Productive Workspace Trends and Tips.pdf
How to Create a Productive Workspace Trends and Tips.pdf
 
Jordan_Amanda_DMBS202404_PB1_2024-04.pdf
Jordan_Amanda_DMBS202404_PB1_2024-04.pdfJordan_Amanda_DMBS202404_PB1_2024-04.pdf
Jordan_Amanda_DMBS202404_PB1_2024-04.pdf
 
Furniture & Joinery Details_Designs.pptx
Furniture & Joinery Details_Designs.pptxFurniture & Joinery Details_Designs.pptx
Furniture & Joinery Details_Designs.pptx
 
Top profile Call Girls In Meerut [ 7014168258 ] Call Me For Genuine Models We...
Top profile Call Girls In Meerut [ 7014168258 ] Call Me For Genuine Models We...Top profile Call Girls In Meerut [ 7014168258 ] Call Me For Genuine Models We...
Top profile Call Girls In Meerut [ 7014168258 ] Call Me For Genuine Models We...
 
Q4-W4-SCIENCE-5 power point presentation
Q4-W4-SCIENCE-5 power point presentationQ4-W4-SCIENCE-5 power point presentation
Q4-W4-SCIENCE-5 power point presentation
 
Top profile Call Girls In Sonipat [ 7014168258 ] Call Me For Genuine Models W...
Top profile Call Girls In Sonipat [ 7014168258 ] Call Me For Genuine Models W...Top profile Call Girls In Sonipat [ 7014168258 ] Call Me For Genuine Models W...
Top profile Call Girls In Sonipat [ 7014168258 ] Call Me For Genuine Models W...
 
UI:UX Design and Empowerment Strategies for Underprivileged Transgender Indiv...
UI:UX Design and Empowerment Strategies for Underprivileged Transgender Indiv...UI:UX Design and Empowerment Strategies for Underprivileged Transgender Indiv...
UI:UX Design and Empowerment Strategies for Underprivileged Transgender Indiv...
 
Anupama Kundoo Cost Effective detailed ppt with plans and elevations with det...
Anupama Kundoo Cost Effective detailed ppt with plans and elevations with det...Anupama Kundoo Cost Effective detailed ppt with plans and elevations with det...
Anupama Kundoo Cost Effective detailed ppt with plans and elevations with det...
 
怎样办理莫纳什大学毕业证(Monash毕业证书)成绩单留信认证
怎样办理莫纳什大学毕业证(Monash毕业证书)成绩单留信认证怎样办理莫纳什大学毕业证(Monash毕业证书)成绩单留信认证
怎样办理莫纳什大学毕业证(Monash毕业证书)成绩单留信认证
 
一比一原版(ANU毕业证书)澳大利亚国立大学毕业证原件一模一样
一比一原版(ANU毕业证书)澳大利亚国立大学毕业证原件一模一样一比一原版(ANU毕业证书)澳大利亚国立大学毕业证原件一模一样
一比一原版(ANU毕业证书)澳大利亚国立大学毕业证原件一模一样
 
poliovirus-190801072449. pptx
poliovirus-190801072449.            pptxpoliovirus-190801072449.            pptx
poliovirus-190801072449. pptx
 
一比一定(购)卡尔顿大学毕业证(CU毕业证)成绩单学位证
一比一定(购)卡尔顿大学毕业证(CU毕业证)成绩单学位证一比一定(购)卡尔顿大学毕业证(CU毕业证)成绩单学位证
一比一定(购)卡尔顿大学毕业证(CU毕业证)成绩单学位证
 
怎样办理伦敦国王学院毕业证(KCL毕业证书)成绩单留信认证
怎样办理伦敦国王学院毕业证(KCL毕业证书)成绩单留信认证怎样办理伦敦国王学院毕业证(KCL毕业证书)成绩单留信认证
怎样办理伦敦国王学院毕业证(KCL毕业证书)成绩单留信认证
 
Top profile Call Girls In Mysore [ 7014168258 ] Call Me For Genuine Models We...
Top profile Call Girls In Mysore [ 7014168258 ] Call Me For Genuine Models We...Top profile Call Girls In Mysore [ 7014168258 ] Call Me For Genuine Models We...
Top profile Call Girls In Mysore [ 7014168258 ] Call Me For Genuine Models We...
 

Epidemiological study designs by anil mph

  • 1. Epidemiological Study Designs: • Broadly, the epidemiological studies may be classified in to the following two broad categories, based on the types of exposure: 1. Observational Study 2. Experimental Study 1 By: Anil Chaudhary (MPH), NOC, Lalitpur, Nepal.
  • 2. According to WHO classification: Observational studies Experimental studies Descriptive study Clinical trial (RCT) Analytical study Field trial Cross sectional study Community trial Ecological study Case control study Cohort study 2 By: Anil Chaudhary (MPH), NOC, Lalitpur, Nepal.
  • 3. 1. Observational studies: in observational study, the researcher has no control over the exposure in another word , the allocation or assignment of factors is not under the control of investigator; he (she) just observe the situation/event and records it, which may be descriptive or analytic. The observational study is also called non-interventional study. 2. Experimental studies: In experimental study, the researcher has control over the exposure, he doesn’t only observe the situation and record it, but also manipulate the situation and measure the effect of manipulation. The experimental study is also known as interventional study. 3 By: Anil Chaudhary (MPH), NOC, Lalitpur, Nepal.
  • 4. Observational studies Descriptive - Case report - Case series - Ecological - D. cross-sectional Analytical - Cohort - Case control - Analytical Cross sectional - A. Ecological By: Anil Chaudhary (MPH), NOC, Lalitpur, Nepal. Observational Study Designs 4
  • 5. Descriptive Studies  Studies that focus on characterizing morbidity or mortality in populations by person, place or time variables.  They do not have a priori hypothesis.  Are not designed to test preconceived suppositions about the relationships between exposure and outcome.  Focus is on describing what exists. By: Anil Chaudhary (MPH), NOC, Lalitpur, Nepal. 5
  • 6. Descriptive study types: 1. Case reports - detailed description of an individual(patient) 2. Case series - Describes characteristics of a group or cluster of individuals with the same disease or symptoms. - Presents a relatively complete profile of case (disease, illness) By: Anil Chaudhary (MPH), NOC, Lalitpur, Nepal. 6
  • 7. Cont… 3. Ecological Study - The unit of analysis is group such as countries, states, cities, hospitals or schools - Investigator have a summary measure of exposure and a summary measure of outcome for each group being studied - Data on exposure and outcome for individual is not collected. - Association is identified only at group level. By: Anil Chaudhary (MPH), NOC, Lalitpur, Nepal. 7
  • 8. Cont… • If we draw conclusion for individual based on ecological study findings we commit an ecological fallacy • Ecological fallacy is an error of reasoning that one commits when group associations are used to draw conclusions about associations at the individual level that may not necessarily exist. By: Anil Chaudhary (MPH), NOC, Lalitpur, Nepal. 8
  • 9. Types of ecological studies Exploratory studies • Descriptive studies that look at variations in outcomes across ecological units such as countries, states etc. • Exposure is not assessed Multiple- group comparison studies • Looks for or test associations between average exposure levels and overall outcome rates. • Generally based on secondary sources By: Anil Chaudhary (MPH), NOC, Lalitpur, Nepal. 9
  • 10. Cont… Time – trend studies Detect changes in the average exposure level and outcome rates for a single population over time Mixed studies Examines changes in average exposure level and outcome rates for several population over time. By: Anil Chaudhary (MPH), NOC, Lalitpur, Nepal. 10
  • 11. Cont… 4. Cross- sectional study • One observes a sample of a population at a single point or brief period of time. • Exposure and outcome assessed at same time period. • The unit of analysis is individual • Also referred as prevalence studies. • Prevalence rates are the usual measure employed in the analysis stages. By: Anil Chaudhary (MPH), NOC, Lalitpur, Nepal. 11
  • 12. Cont… a b c d Present (Dis.) Absent (Dis.) Outcome Status Exposure Status Exposed Unexposed a+ b c+ d a + c b+ d n (a+b+c+d) Crude Prevelance rate (PR) = {(a+c)/n} * 100 PRe = [a/(a+b)]*100 PRue = [c/(c+d)]*100 By: Anil Chaudhary (MPH), NOC, Lalitpur, Nepal. 12
  • 13. Analytical studies • Analytical studies are designed to test hypothesis about the association between an exposure of interest and a particular outcome. By: Anil Chaudhary (MPH), NOC, Lalitpur, Nepal. 13
  • 14. Case control studies • Begins by classifying subjects according to their outcome status. • Cases of the disease being investigated are selected along with a comparable group of control who do not have the outcome in question. • The cases and controls are then examined for exposure of interest. • In case control study one is going from effect to cause. • Cases and controls are selected and data are collected about past exposure that may have contributed to disease. By: Anil Chaudhary (MPH), NOC, Lalitpur, Nepal. 14
  • 15. Cont…  Seeks to identify possible cause of the disease by finding out how the cases and controls differ.  Takes into consideration that the case groups must have been exposed to some factors that contributes to the causation of their disease.  Compares the frequency of exposure among cases and controls By: Anil Chaudhary (MPH), NOC, Lalitpur, Nepal. 15
  • 16. Schematic Diagram of Case Control Study Design By: Anil Chaudhary (MPH), NOC, Lalitpur, Nepal. 16
  • 17. Selection of cases  First step: Establishing the diagnostic criteria and definition of disease.  Incidence (new cases) - preferred  Prevalence cases are more difficult to link a specific cause with a disease outcome – because it is influenced by the development and duration of disease. By: Anil Chaudhary (MPH), NOC, Lalitpur, Nepal. 17
  • 18. Selection of cases • Sources of cases: – Records from public health clinics – Physician offices – Health maintenance organizations – Hospitals – Industrial and government sources. • Cases should be representative of all persons with the disease. By: Anil Chaudhary (MPH), NOC, Lalitpur, Nepal. 18
  • 19. Selection of cases • All persons with the disease may be included in the study. • However, random selection is required. • A large random sample from a population of interest ensures the results can be appropriately generalized. • Researchers can use restriction (limiting subjects to certain characteristics) to reduce potential bias and to increase feasibility. By: Anil Chaudhary (MPH), NOC, Lalitpur, Nepal. 19
  • 20. Selection of controls • In order to ensure a valid and reliable case-control study, the controls should look like cases with the exception of not having the disease. • Controls should be selected from the same population as the cases. • Controls should be representative of general population. • Controls should have the same probability of being selected and exposed as the cases. By: Anil Chaudhary (MPH), NOC, Lalitpur, Nepal. 20
  • 21. Selection of controls • Sources of controls: – General population as cases – Same hospital as cases – Family, friends, or relatives of cases • In some circumstances, selecting more than one control group may be useful. • It may also be useful to select more controls when few cases are available. This increases power of the study • The ratio of controls : cases should not exceed 4 : 1. By: Anil Chaudhary (MPH), NOC, Lalitpur, Nepal. 21
  • 22. Exposure Status • Information about exposure status can be obtained through – Medical records – Interviews – Questionnaires – Surrogates (such as spouses, siblings, or employers) • Information on exposure status between cases and controls should be collected in a similar manner (in order to avoid bias). • Blinding interviewers or those assessing medical records to cases and controls may further minimize bias.By: Anil Chaudhary (MPH), NOC, Lalitpur, Nepal. 22
  • 23. Exposure Status • Preferable to blind those performing the assessment to the hypothesis of the study (because such knowledge could influence how they probe or scan records for information). By: Anil Chaudhary (MPH), NOC, Lalitpur, Nepal. 23
  • 24. Measure of association • Commonly used measure of the relative probabilities of disease in case-control studies is ODDS RATIO (relative odds). • ODDS RATIO: is appropriate for measuring the strength of association between exposure and disease variables. By: Anil Chaudhary (MPH), NOC, Lalitpur, Nepal. 24
  • 25. ODDS RATIO Cases Controls Total Exposed a b a + b Unexposed c d c + d Total a + c b + d N = a + b + c + d Odds of exposure among case group = [a/(a+c)]÷ [c/(a+c)] = a/c Odds of exposure among control group = b/d Odds Ratio (OR) = (a/c) ÷ (b/d) or ad/bc Odds of an event can be defined as the ratio of the proportion of cases exposed to proportion of cases not exposedBy: Anil Chaudhary (MPH), NOC, Lalitpur, Nepal. 25
  • 26. ODDS RATIO (OR) • If the OR = 1, this indicates no association between exposure and disease. • If the OR > 1, this indicates a positive association between exposure and disease. • If the OR < 1, this indicates a negative association between exposure and disease. By: Anil Chaudhary (MPH), NOC, Lalitpur, Nepal. 26
  • 27. Cohort study • A cohort is defined as a population group, or subset thereof ( distinguished by a common characteristics), that is followed over a period of time. • Best method for determining the incidence and natural history of a condition. • Because data on exposure and disease refer to different points in time, cohort studies are longitudinal in nature. • In single cohort studies, those who do not develop the disease are used as internal controls. • When two cohorts are used, one group has been exposed or treated with an agent; and the other group not treated with agent act as external controls. By: Anil Chaudhary (MPH), NOC, Lalitpur, Nepal. 27
  • 28. Cont… • Start with a population at risk • Measure characteristics at baseline • Follow-up the population over time with surveillance or re- examination • Compare events rates in people with and without characteristics of interest – Study participants may be either fixed (subjects do not vary over time and dropouts are not replaced) or dynamic (where new subjects enter the study in accordance with eligibility criteria. By: Anil Chaudhary (MPH), NOC, Lalitpur, Nepal. 28
  • 29. Schematic Diagram of Cohort Study Design By: Anil Chaudhary (MPH), NOC, Lalitpur, Nepal. 29
  • 30. Prospective cohort studies (90%) • The term prospective refers to the timing of data collection and not to the relationship between exposure and effect. • In this type of study, a group of people are chosen who do not have outcome of interest on the basis of exposure and followed for a long time until the events occur. • The cohort are then followed longitudinally into the future to determine if the rate of development of the study outcome is significantly higher in the exposed group compared to unexposed group. By: Anil Chaudhary (MPH), NOC, Lalitpur, Nepal. 30
  • 31. Retrospective Cohort (10%) • Makes us of historical data to determine exposure level at some base line in the past • Follow up for subsequent occurrence of disease between baseline and the present is performed. • The cohort is considered historical as it represents a group of people once they were in the past. • Once cohort has been identified, next step is to classify subjects by exposure status. By: Anil Chaudhary (MPH), NOC, Lalitpur, Nepal. 31
  • 32. Measure Disease No disease Total Exposed a b a + b Unexposed c d c + d Total a + c b + d N = a + b + c + d Relative Risk = Incidence rate in the exposed / Incidence rate in the non exposed = [a/(a+b)] ÷ [c/(c+d)] By: Anil Chaudhary (MPH), NOC, Lalitpur, Nepal. 32
  • 33. Cont… • RR = 1 , implies that the risk(rate) of disease among the exposed is no different from the risk of disease among the non exposed • RR>1, implies risk is high among exposed • RR<1, Implies exposure is not fully associated with risk of disease By: Anil Chaudhary (MPH), NOC, Lalitpur, Nepal. 33
  • 34. Experimental Study Designs 1. Randomized Control Trials 2. Non Randomized Trials By: Anil Chaudhary (MPH), NOC, Lalitpur, Nepal. 34
  • 35. Randomized Control Trial • Is an experiment where individual subjects are randomly assigned to either an experiment or control group to assess the effects of a preventive or therapeutic agent, treatment, procedure, or service. By: Anil Chaudhary (MPH), NOC, Lalitpur, Nepal. 35
  • 36. RCT:Can be grouped into 3 categories 1. Preventive Trials 2. Therapeutic trials 3. Intervention trials By: Anil Chaudhary (MPH), NOC, Lalitpur, Nepal. 36
  • 37. Design and analysis of a RCT may be considered in ten stages: 1. Specification of the program 2. Subject selection 3. The observation 4. Allocation of subject 5. The control group 6. Required no of subjects 7. Control of subjective factors 8. Follow up 9. Outcome 10. analysis By: Anil Chaudhary (MPH), NOC, Lalitpur, Nepal. 37
  • 38. Process 1. Develop the hypothesis 2. Selection of sample First, Reference population must be specified Next, identify experimental population Finally, sample population is determined. Eligibility criteria( exclusion and inclusion) By: Anil Chaudhary (MPH), NOC, Lalitpur, Nepal. 38
  • 39. 3. Allocate subjects into Experimental and Control groups Randomization The subjects have same probability of being assigned to both group By: Anil Chaudhary (MPH), NOC, Lalitpur, Nepal. 39
  • 40. 4. Apply the intervention - Experimental group exposed to promising but unproven agent, treatment, procedure or service - Control group exposed to either a placebo or the customary treatment for the problem By: Anil Chaudhary (MPH), NOC, Lalitpur, Nepal. 40
  • 41. 5 . Assess the outcome during follow up - Subjects are followed up prospectively - Assessment of outcomes during follow up may be subject to measurement bias - Bias can occur when subjects are aware of which group they have been assigned to - Placebo effect can occur By: Anil Chaudhary (MPH), NOC, Lalitpur, Nepal. 41
  • 42. Bias can be minimized through blinding (masking) - Single blinding: A single blind experiment only the participant does not know whether they are part of the treatment or control group, - Double blinding: A double-blind experiment both the participant and the experimenter are kept in the dark as to who is in the treatment and who is in the control group By: Anil Chaudhary (MPH), NOC, Lalitpur, Nepal. 42
  • 43. Randomized Control Trial (RCT): By: Anil Chaudhary (MPH), NOC, Lalitpur, Nepal. 43
  • 44. Other designs of randomized control trials 1. Restricted randomization :  randomization and comparison is done within strata 2. Sequential analysis : no. of observation not fixed in advance Data continuously analyzed Trial interrupted as soon as a statistical significance is reached By: Anil Chaudhary (MPH), NOC, Lalitpur, Nepal. 44
  • 45. Cont… 3. Factorial design • Simultaneous evaluation of two or more treatment as well as their outcomes 4. Trials on collective units • Random distribution of group of individuals By: Anil Chaudhary (MPH), NOC, Lalitpur, Nepal. 45
  • 46. Difficulties in application of RCT for evaluation - Randomization is not always possible (ethical issues ) - Randomization does not answer the crucial questions, regarding what is the actual impact - Comparability resulting from randomization is frequently partly destroyed (double blinding rarely applicable) - The randomized comparison of individual components impossible as evaluation is multidimensional By: Anil Chaudhary (MPH), NOC, Lalitpur, Nepal. 46
  • 47. Non randomized trials • A study where participants have been assigned to the treatment, procedure, or intervention alternatives by a method that is not random. The investigator defines and manages the alternatives • It do not meet the criteria for a true experimental design By: Anil Chaudhary (MPH), NOC, Lalitpur, Nepal. 47
  • 48. When is it appropriate to use a non-randomized trial design? • When the act of random allocation may reduce the effectiveness of the intervention • When it would be unethical to do random allocation • When it is impractical to do random allocation  (e.g. cost or convenience factors) • When there are legal or political obstacles to random allocation By: Anil Chaudhary (MPH), NOC, Lalitpur, Nepal. 48
  • 49. Various types - Uncontrolled trials with a single examination after the intervention - Before and after comparison - Controlled non randomized trials - Non randomized controlled trials based on collective units By: Anil Chaudhary (MPH), NOC, Lalitpur, Nepal. 49
  • 50. By: Anil Chaudhary (MPH), NOC, Lalitpur, Nepal. 50