Association and Causation

Association and Causation
Dr S Kar
SMIMS
Introduction
• The fundamental objective of epidemiology is the
identification of the causes of disease through the
appropriate study of the distribution of cases within
groups of humans with a range of identified characteristics,
such as different levels of exposure to an agent.
• Epidemiological studies help to confirm the observed
association between suspected cause and disease. The
epidemiologist tries to establish a ‘cause and effect’
relationship.
• Scientific studies that show an association between a

factor and a health effect do not necessarily imply that the
factor causes the health effect
• e.g. . Altitude and endemic goitre. Endemic
goitre is generally found in high altitudes,
showing an association between altitude and
endemic goitre. But endemic goitre is not due
to altitude but due to iodine deficiency. That
implies that the statistical association does
not necessarily mean causation.
Contd…….
Most epidemiological studies are by nature

observational rather than experimental, a number
of possible explanations for an observed
association need to be considered before we can
infer a cause-effect relationship exists.
That is, the observed association may in fact be
due to the effects of one or more of the following:
• Chance (random error)
• Bias (systematic error)
• Confounding
Association
• The term ‘association’ and ‘relationship’ are often
used interchangeably.
• Association may be defined as the concurrence of
two variables more often than one would expect by
chance. In other words , events are said to be
associated when they occur more frequently together
than one would expect by chance.
• Correlation indicates the degree of association
between two characteristics. However, correlation
cannot be used to evoke causation, because the
sequence of exposure preceding disease cannot be
assumed to have occurred. And also correlation does
not measure the risk.
Contd.
Association can be grouped under three headings.
• Spurious association
• Indirect association
• Direct One - to - one causal association
• Multifactorial association
Spurious association.
• Spurious association. Sometimes an observed
association between a disease and suspected factor
may not be real.
For example, a study in UK showed that perinatal
mortality rates of 5.4 per 1000 in the home births,
and 27.8 per 1000 in the hospital births.
Apparently, the perinatal mortality was higher in the
hospital births than in the home births. It might be
concluded that homes are safer place for deliveries
than hospitals. Such a conclusion is spurious or
artifactual.
Indirect association
Many associations which at first appeared to be

causal have been found on further study to be
due to indirect association.
The indirect association is a statistical
association between a characteristic of interest
and a disease due to the presence of another
factor, known or unknown. This third factor is
also known as ‘confounding’ variable. Such a
confounding variable (e.g. age, sex, social class)
are probably present in all data.
Direct (causal) association
• One – to – one causal relationship.
Two variables are stated to be causally
related (AB) if a change in A is followed by a
change in B. if it does not, then their relation
cannot be causal. This is known as one – to –
one causal relationship. This model suggests
that when the factor A is present, the disease
B must result.
Multifactorial causation
• The causal thinking is different when we
consider a non-communicable disease or
condition where the etiology is
multifactorial.
Alternative causal factors each acting

independently. It is possible that various
factors can independently cause cellular level
reaction. The cellular factor then be
considered as a causal factor.
Criteria for causal association
• In 1965 Austin Bradford Hill detailed some
criteria for assessing evidence of causation.
These guidelines are sometimes referred to
as the Bradford-Hill criteria, but this makes it
seem like it is some sort of checklist. For
example, Phillips and Goodman (2004) note
that they are often taught or referenced as a
checklist for assessing causality, despite this
not being Hill's intention
CAUSALITY OF AN ASSOCIATION
Useful, time-tested criteria for determining whether

an association is causal include
– Temporal Association- For an association to be causal,
the cause must precede the effect.
– Strength of Association. As noted earlier, the greater
the magnitude of risk or benefit, the less likely the
association is to be spurious or due to confounding
bias. However, a causal association should not be ruled
out simply because a weak association is observed.
– Dose-response. Responses that increase in frequency
as exposure increases are more convincingly
supportive of causality than those that do not show
this pattern.
Contd.
– Consistency. Relationships that are repeatedly observed
by different investigators, in different places,
circumstances, and times, are more likely to be causal.
– Biological plausibility. Associations that are consistent

with the scientific understanding of the biology of the
disease or health effect under investigation are more
likely to be causal.
– Reversibility. An observed association leads to some

preventive action, and removal or reduction of the
exposure should lead to a reduction of disease or risk of
disease
Strength of an Association
• An increased risk of less than 50% (RR=1.0–1.5) or a
decreased risk of less than 30% (RR=0.7–1.0) is considered
by many epidemiologists to be either a weak association or
no association.
• Confounding can lead to a weak association between

exposure and disease, and it is usually not possible to
identify and adequately measure or control weak
confounding characteristics. For weak associations,
investigators should thoroughly evaluate the possibility that
the association is affected by uncontrolled confounding. On
the other hand, a very large increased or decreased RR is
unlikely to be completely explained by an unidentified or
uncontrolled confounding factor
Strength of Association
Conclusion
• An observed statistical association between a
risk factor and a disease does not necessarily
lead us to infer a causal relationship.
Conversely, the absence of an association
does not necessarily imply the absence of a
causal relationship.
• According to Rothman, the only criterion that
is truly a causal criterion is temporality.
Web of causation
This model of disease causation was

suggested by Mac Mahon and Pugh. This
model is suited in the study of chronic
diseases of which the exact cause is not
known.
The web of causation considers all the
predisposing factors of any type and their
complex interrelationship with each other
How to establish causal inference
• For infectious disease - Koch’s postulate
• For Chronic disease - Hill’s criteria

Association and Causation

Uploaded by

Copyright:

Available Formats

Association and Causation

Uploaded by

Document Information

Original Description:

Copyright

Available Formats

Share this document

Share or Embed Document

Sharing Options

Did you find this document useful?

Is this content inappropriate?

Copyright:

Available Formats

Association and Causation

Uploaded by

Copyright:

Available Formats

Association and Causation

• Scientific studies that show an association between a

Most epidemiological studies are by nature

Many associations which at first appeared to be

Alternative causal factors each acting

Useful, time-tested criteria for determining whether

– Biological plausibility. Associations that are consistent

– Reversibility. An observed association leads to some

• Confounding can lead to a weak association between

This model of disease causation was

• For infectious disease - Koch’s postulate

• For Chronic disease - Hill’s criteria

You might also like