This presentation provides overview of three observational analytical studies: cross-sectional study design, case-control study design and cohort study design
3. Cross-Sectional Study
• Cross-sectional studies are observational studies in which
exposure and outcome are analyzed simultaneously (at a
single point in time).
• These studies are also known as prevalence studies, since they
enable calculation of disease frequency in a particular sample.
• They can determine
• the presence or absence of a disease (such as the percentage of
people with lung cancer) or
• exposure to a particular causal factor at a particular time (such as the
influence of smoking on coronary disease).
4. Cross-Sectional Study
• They are also often used to determine the diagnostic
characteristics of a test, by comparing it to a gold standard and
deriving the classic measures of association.
• The measure of association in cross-sectional studies is
prevalence.
6. Design of Cross-Sectional Study
Formal Structure of Design
• In a cross-sectional study all measurements are made at one
time point. Its formal structure is similar to that of a cohort study,
except for the time at which the measurements are made.
• Unlike cohort studies, in cross-sectional studies there is no
clear time relation between exposure and outcome.
7. Design of Cross-Sectional Study
Sample Selection
• Selection of the study groups naturally begins by selecting the
relevant population.
• The next step after determining the population is to select a
sample. i.e. those who will be the subjects of the study. In larger
populations, sampling may be systematic or random.
8. Design of Cross-Sectional Study
Analysis of measures of association
• The measure of association in cross-sectional studies is
prevalence, the ratio between the diseased subjects at one
point in time and all subjects at risk at the point of time.
• We may also calculate odds ratios to measure the strength of
association
• Findings of prevalence surveys must be interpreted cautiously;
the mere fact that two variables are associated does not mean
that they are causally related.
10. Example 1
• We are interested to know the prevalence of anemia among
pregnant women in a village.
• We design a population-based survey to assess the prevalence
of this condition. We go to all the households having pregnant
(that were supposed to be included in the study) and examine
the population.
• Suppose, the total sample surveyed is 287. Of these, we found
that 192 pregnant women were anemic.
• 153 anemic women and 53 non-anemic women had parasitic
infection
11. Example 1:
Calculate
• Anemia prevalence in the study population
• Anemia prevalence among women having parasitic infestation
• Calculate anemia prevalence among women not having
parasitic infestation (odds of anemia among unexposed)
• Odds of anemia among exposed
• Odds of anemia among non-exposed
• Odds of exposure among anemic
• Odds of exposure among non-anemic
14. Example 1
• Calculate the anemia prevalence in the
study population
• 192/287 = 66.899% =66.90%
• Calculate anemia prevalence among
women having parasitic infection
• 153/206 = 74.3%
• Calculate anemia prevalence among
women not having parasitic infection
• 39/81 = 48.1%
Anemia
present
Anemia
not
present
Total
Parasitic
Infection
153
(a)
53
(b)
206
No
parasitic
infection
39
(c)
42
(d)
81
Total 192 95 287
15. Example 1
• Odds of anemia among exposed
• a/b = 153/53 =2.89
• Odds of anemia among non-exposed
• c/d = 39/42 = 0.93
• Odds of exposure among anemic
• a/c = 153/39 = 3.92
• Odds of exposure among non-anemic
• b/d = 53/42 = 1.26
Anemia
present
Anemia
not
present
Total
Parasitic
Infection
153
(a)
53
(b)
206
No
parasitic
infection
39
(c)
42
(d)
81
Total 192 95 287
16. Strengths and Limitations
Strengths
• No need to wait for the outcome, and so there are no risks for
loss to follow up;
• It is the only study design that can determine the disease
prevalence;
• It can be accomplished in short duration of time as compared to
other studies
17. Strengths and Limitations
Strengths
• These are studies are conducted either before planning a
cohort study or a baseline in a cohort study.
• Several outcomes can be studied at the same time
• These study designs may be useful for public health planning,
monitoring, and evaluation. For example, the National AIDS
Program conducts cross-sectional IBB survey among high-risk
groups to monitor the prevalence of HIV in these groups.
18. Strengths and Limitations
Limitations
• Impossible for rare predictors or outcomes
• Impossible to establish a sequence of events
• Cannot be used to calculate incidence or relative risk
• Cannot establish causality or the natural history or prognosis of
a disease
20. Case-Control Study
• In this design, participants are selected for the study based on
their outcome status.
• A number of cases and non-cases (controls) are identified, and
the occurrence of one or more prior exposures is compared
between groups to evaluate exposure–outcome associations.
• A case–control study runs in reverse relative to a cohort study.
21. When to use a case-control design
• To investigate risk factors for a rare disease where a
prospective study would take too long to identify sufficient cases
• To investigate an acute outbreak in order to identify causal
factor quickly.
23. Design of Case-Control Study
Selection of cases
• It is essential that the case definition is clearly defined at the
outset of the investigation to ensure that all cases included in
the study are based on the same diagnostic criteria.
• Sometimes, definition of a disease may be based on multiple
criteria; thus, all these points should be explicitly stated in case
definition.
• Sources of cases needs to be clearly defined
24. Design of Case-Control Study
Selection of cases
• Cases may be recruited from a number of sources; for example they
may be recruited from a hospital, clinic, or may be population based.
• Selecting only hospital-based cases may lead to systematic error
related to hospital admission practices (a phenomenon known as
Berksonian bias).
• Population based case control studies are generally more expensive
and difficult to conduct.
• Preferably, new (incident) cases should be selected, as non-incident
cases usually over-represent long-term survivors, and diagnostic
practices may change over time, introducing potential bias.
25. Design of Case-Control Study
Selection of controls
• The next important point in designing a case-control study is the
selection of control.
• Essentially, the controls should come from a population with the
same exposure distribution as the cases.
• Common choices of control include
• Hospital Control: Patients in the same hospital but with unrelated disease or
conditions
• Relative/friend controls
• Population controls: A random sample of the population from which the
cases come
• Clearly the best control group is the third option, but this is expensive
and time consuming
26. Design of Case-Control Study
Matching
• Matching is often used in case-control control studies to ensure
that the cases and controls are similar in certain characteristics.
• For example, in the smoking and lung cancer study, the authors
select controls that are similar in age and sex to carcinoma
cases.
• Matching is a useful technique to increase the efficiency of
study.
• ‘Individual matching’ is one common technique used in case-
control study.
27. Design of Case-Control Study
Matching
• Matching may be useful to control for certain types of
confounders.
• For instance, environment variables may be accounted for by
matching controls for neighborhood or area of residence.
• Household environment and genetic factors may be accounted
for by enrolling siblings as controls.
28. Design of Case-Control Study
Measurement of exposure status
• Exposure status is measured to assess the presence or level of
exposure for each individual for the period of time prior to the
onset of the disease or condition under investigation when the
exposure would have acted as a causal factor.
• In case-control studies the measurement of exposure is
established after the development of disease and as a result is
prone to both recall and observer bias.
29. Design of Case-Control Study
Analysis of measure of association
• In a case-control study, the odds ratio is the usual measure of
association reported.
• This measure is the ratio of the odds of an exposure between
cases and controls.
• Since we are not able to measure incidence data in case-
control study, an odds ratio is a reasonable measure of the
relative risk (under some assumptions).
31. Additional Points
What should be the ratio of cases : control?
• The most optimum case-to-control ratio is 1:1.
• For a fixed sample size, the chi square test for independence is most
powerful if the number of cases is same as the number of controls.
• However, in many situations we may not be able recruit a large number of
cases and it may be easier to recruit more controls for the study.
• We can increase the number of controls to increase statistical power (if we
have limited number of cases) of the study.
• If data are available at no extra cost, then we may recruit multiple controls
for each case.
• However, if it is expensive to collect exposure and outcome information
from cases and controls, then the optimal ratio is 4 controls: 1 case.
32. Strengths and Limitations
Strengths
• They are efficient for rare diseases or diseases with a long latency
period between exposure and disease manifestation (e.g.
melanoma).
• Cost-effective relative to other analytical studies such as cohort
studies.
• It is also useful to study multiple exposures in the same outcome.
• No problems of attrition (loss to follow up)
• No risks to subjects. So, ethical problems are minimal
• Case-control studies are useful to study the association of risk
factors and outcomes in outbreak investigations.
33. Strengths and Limitations
Limitations
• Not useful to study rare exposures. It may be prudent to
conduct a cohort study for rare exposures
• The design is not useful to study multiple outcomes.
• Sometimes the temporality of the exposure and outcome may
not be clearly established in case-control studies
• Prone to certain biases (selection, observer and recall bias)
• Selection of control may be difficult
34. For further reading about case-control
study
• Methodology Series Module 2: Case-control Studies:
https://www.ncbi.nlm.nih.gov/pmc/articles/PMC4817437/
• https://www.healthknowledge.org.uk/e-
learning/epidemiology/practitioners/introduction-study-design-
ccs
36. Nested Case Control Study
• A nested case-control study is a type of case-control study that
draws its cases and controls from a cohort population that has
been followed for a period of time.
• A nested-case control study depends on the pre-existence of a
cohort that has been followed over time.
• This cohort, at its inception or during the course of follow-up,
has had exposure information collected that are of interest to
the investigator.
37. Nested Case Control Study
• The investigator identifies cases of disease that occurred in the
cohort during the follow-up period.
• The investigator also identifies disease-free individuals within
the cohort to serve as controls.
• Using previously collected data and obtaining additional
measurements of exposures from available bio-specimens, the
investigator compares the exposure frequencies in cases and
controls as in a non-nested case-control study
39. Example of Nested Case-Control Study
• Breast Cancer Occurrence Among Women With or Without DDT
Exposure
40. Strengths and Limitations
Strengths
• It is more efficient than a cohort design. i.e. it can detect differences
as statistically significant with a smaller sample size than that
required for a cohort analysis.
• Exposure histories are not subject to recall bias because they are
determined before the cases are diagnosed.
• This design also avoids the potential bias of not including fatal cases
and may minimize the potential bias of non-participation, since
exposure data is collected before diagnosis of disease.
• It also minimizes selection bias introduced when cases and controls
are not selected from the same populations.
• Eliminates suspicion bias
41. Strengths and Limitations
Limitations
• Data on exposure must be collected on the entire cohort at
baseline. Therefore the cost of data collection is likely to be
higher than traditional case control study.
• The time required is longer and less suitable for very rare
disease or those with long latent periods
43. Cohort Study
• Study design used to investigate the cause of disease and to
establish links between risk factors and health outcomes.
• A group of individuals (Cohort) is followed over time (often
years) to determine the occurrence of disease
• exposed /unexposed to the risk factor.
• The incidence of disease in the exposed group is compared
with the incidence of disease in the unexposed group.
44. Features of Cohort Study
• The cohorts are identified prior to the appearance of the
disease under investigation
• The study groups are observed over a period of time to
determine the frequency of disease among them.
• The study proceeds forward from cause to
effect.(exposure>>outcome)
46. Design of Cohort Study
1. Selection of study participants
• The participants of a cohort study are usually assembled either
from general population or select groups of the population that
can be readily studied
• E.g.: persons with different degrees of exposures to the suspected
causal factor
• The cohorts must be free from the disease under study.
47. Design of Cohort Study
2. Obtaining data on exposure
• Exposure information should be collected in such a manner that
the study group can be classified according to the degree of
exposure.
• Information about the exposure may be obtained from number
of sources
• From cohort members through interview or mailed questionnaire
• Review of records
• Medical examination or special tests
• Environmental surveys
48. Design of Cohort Study
3. Selection of comparison group
a. Internal comparison:
• A single general cohort is entered in the study
• Then its members are classified into different exposure groups on the
basis of information obtained before the development of disease.
b. External comparison:
• When information on degree of exposure is not available, it is
necessary to put up an external control, to evaluate the experience of
the exposed group.
• E.g., a cohort of radiologist can be compared with cohort of
ophthalmologist to investigate the effect of radiation on development of
malignancy.
49. Design of Cohort Study
3. Selection of comparison group
c. Comparison with general population rates
• If none is available, the morbidity/mortality experience of the exposed
group is compared with the experience of the general population in the
same geographic area as the exposed people.
• E.g., comparison of frequency of cancer among asbestos workers with
the rate in general population in the same geographic area.
50. Design of Cohort Study
4. Follow up
• At the beginning of the study, method should be developed to
obtain data for assessing the outcome.
• The entire study participant should be followed up from point of
exposure.
5. Analysis of measure of association
• For cohort studies, the exposure outcome association is usually
expressed as
• relative risk or
• incidence rates of outcome among exposed and non-exposed.
51. Types of Cohort Study
1. Prospective cohort studies
• Prospective cohort study is one in which the outcome has not
yet occurred at the time the investigation begins.
• The study subjects are classified on the basis of presence or
absence of exposure and followed up to find the development of
the outcome of interest.
52. Types of Cohort Study
2. Retrospective (historical) cohort study
• The subjects are classified on the basis of presence or absence
of exposure but in this type the exposure and the outcome of
interest have already occurred at the beginning of the study.
• A historical cohort study depends upon the availability of good
data or records that allow the reconstruction of the exposure of
cohorts to a suspected risk factor.
53. Types of Cohort Study
3. Combination of retrospective and prospective cohort
studies
• In this type of study, both the retrospective and prospective
elements are combined.
• The cohort is identified from past records, and is assessed of
date for the outcome.
• The same cohort is followed up prospectively into future for
further assessment of outcome.
54. Strengths and Limitations
Strengths
• The temporal sequence i.e. exposure preceding outcome is
explicit in the study design
• Cohort studies are relatively efficient for studying rare
exposures.
• Multiple outcomes may be assessed for a single exposure.
• The incidence of a particular outcome among persons exposed
can be directly calculated.
55. Strengths and Limitations
Limitations
• Long observation periods may be more susceptible to losses to
follow-up (attrition) and to inaccurate measurement of
exposures and outcomes.
• They are unsuitable for investigating rare diseases or
diseases with low incidence.
• Since the study take place for longer periods, it is difficult to
keep large number of people under surveillance indefinitely.
• Cohort studies are expensive.
58. For further reading
• Song, J. W., & Chung, K. C. (2010). Observational studies: cohort and
case-control studies. Plastic and reconstructive surgery, 126(6), 2234–
2242. https://doi.org/10.1097/PRS.0b013e3181f44abc
• https://www.healthknowledge.org.uk/e-
learning/epidemiology/practitioners/introduction-study-design-cs