CONTENTS

• Association
– Types of Association
– Measures of Association

• Causation
– Models of causation
– Criteria for causality (HILL’s Criteria)

• Brief discussion on Correlation and Regression

 ASSOCIATION
An association is present if the probability of occurrence of an
event or characteristic, or the quantity of a variable, depends upon
the occurrence of one or more other events, the presence of one or
more other characteristics, or the quantity of one or more other
variables1.
Association may be defined as the concurrence of two variables
more often than would be expected by chance2.

Reference – 1.JOHN M.LAST; 2.PARK

 Environmental exposure or Host characteristic

Is an association If an association Is the observed

observed is observed association Casual???

Disease or health outcome

IF AN ASSOCIATION IS OBSERVED
• IS IT REAL OR SPURIOUS ASSOCIATION???
• Interpreting REAL association-
a) INDIRECT ASSOCIATION(mostly due to confounding)
OR
b) CAUSAL ASSOCIATION-- 1.Direct causation
A. One-to-One Causal Relationship
B. Multi-Factorial Causation
2. Indirect causation
TYPES OF ASSOCIATION
 SPURIOUS ASSOCIATION
• Observed association between an outcome and suspected factor is not
real.
• This Fallacy of presumption arises when two variables are improperly
compared (due to Bias).
• E.g. a study was conducted between births at home and births in
hospital.
• Apparently perinatal mortality was observed to be more in the
newborns born in a hospital than those born at home.
• It may be concluded that home deliveries are safer than hospital
deliveries.
• Such a conclusion is spurious because in general, hospitals attract
women at high risk for delivery because of their special equipment
and expertise.
INDIRECT ASSOCIATION
• The indirect association is a association between a characteristics
(or variable) of interest and a disease due to the presence of
another factor, known or unknown, that is common to both the
characteristic and the disease. This third factor i.e. the common
factor is also known as the confounding factor.
• Examples:
– Increased coffee drinking and increased risk of pancreatic cancer
Increased Coffee Drinking
Smoking
Increased risk of Ca Pancreas

– Increased cholesterol and increased risk of CHD Increased Cholesterol

Factor X
Increased risk of CHD
CAUSAL ASSOCIATION
1. One-to-one Causal Relationship
• The variables are stated to be casually related (AB) if a change in A is followed by a
change in B.
• When the disease is present, the factor must also be present.
A B
For e.g. (a) A trauma to the skin results in a bruise or infection
(b) Salmonella results in enteritis
• But a single factor or cause may lead to more than one outcome
• Hemolytic Streptococci Erysipelas
• Scarlett Fever
Tonsillitis
2. Multi-Factorial Causation
• A given disease or other outcome may have more than one cause.
• A combination of causes or alternative combinations of causes may be required
to produce the effect.
• The factors act independently or cumulatively.
• Eg. Both Asbestos exposure and Smoking cause Lung Cancer independently and
cumulatively
3.Indirect causal Association
In indirect causation a factor causes a disease but only through intermediate step
or steps.
Factor A Step 1 Step 2 Disease
For e.g. Poor diet and stress may cause high blood pressure, which in turn causes
heart disease.
 CAUSAL RELATIONSHIPS
If a Relationship is Causal, Four Types of causal relationships are possible:

• Necessary and Sufficient

• Necessary But not Sufficient
• Sufficient But not Necessary
• Neither Necessary nor Sufficient
NECESSARY AND SUFFICIENT

• A Factor is both necessary and sufficient for producing the disease.

• Without that factor, the disease never develops (the factor is
necessary), and in the presence of that factor, the disease always
develops (the factor is sufficient).
• Eg- the measles virus is necessary to cause measles in an
unimmunized individual or population.

Factor A Disease
 NECESSARY BUT NOT SUFFICIENT

• Each factor is necessary, but not, in itself, sufficient to cause the disease
• Thus, multiple factors are required, often in a specific sequence.
• Eg. Mycobacterium tuberculosis is the necessary cause of tuberculosis
but often is not a sufficient cause without poverty, poor nutrition,
overcrowding, etc.

Factor A

Factor B Disease

Factor C
SUFFICIENT BUT NOT NECESSARY

• The factor alone can produce the disease, but so can other factors
that are acting alone.
• But the criterion of sufficient is rarely met by a single factor.
• Eg. Lung cancer can be caused by cigarette smoking, asbestos
• fibers, or radon gas.

Factor A
or
Factor B Disease
or
Factor C
 NEITHER NECESSARY NOR SUFFICIENT

• A Factor, by itself, is neither sufficient nor necessary to produce disease.

• This is a more complex model, which probably most accurately
represents the causal relationships that operate in most chronic
diseases.

Factor A Factor B
or
Factor C Factor D Disease
or
Factor E Factor F
 IF THE ASSOCIATION IS DUE TO CHANCE, IT
COULD BE BECAUSE OF :
• 1.Bias
• 2.Confounding
• 3. Ecological fallacy

Ref J.Hopkin’s lecture 19

BIAS
Bias is a systematic error in the design, conduct or analysis of a
study that results in a mistaken estimate of an exposure’s effect on
the risk of disease

• —(Schlesselman and Stolley, 1982)

TYPES OF BIAS
Selection bias
Is a method of participant selection that distorts the exposure-
outcome relationship from that present in the target population
Selection bias occurs when the selection of participants in one
group results in a different outcome than the selection for the
other group
Controlling Selection Bias

• Define criteria of selection of diseased and non-diseased

participants independent of exposures in a case-control study
• Define criteria of selection of exposed and non-exposed
participants independent of disease outcomes in a cohort study
• Use randomized clinical trials
Information bias
• Occurs when information is collected differently between two
groups, leading to an error in the conclusion of the association
• When information is incorrect, there is misclassification
• In Differential misclassification the rate of misclassification
differs in different study group.
• In Non-differential misclassification results from the degree of
inaccuracy that characterizes how information is obtained from
any study group either cases and controls or exposed and non-
exposed. It is just a problem inherenting data collection
methods.
Interviewer knows the status of the subjects before the interview
process Interviewer may probe differently about exposures in the
past if he or she knows the subjects as cases(interviewer bias)

• Subjects may recall past exposure better or in more detail if he

or she has the disease (recall bias)
Controlling Information Bias
Have a standardized protocol for data collection
• Make sure sources and methods of data collection are similar for
all study groups
• Make sure interviewers and study personnel are unaware of
exposure/disease status
 CONFOUNDING
Confounding occurs when the observed result between exposure and disease
differs from the truth because of the influence of the third variable.
In a study of whether Factor A is a risk factor for Disease B, X is a confounder if:
• 1. It is a risk factor for Disease B

• 2. It is associated with Factor A (but is not a result of exposure to factor A)

• 3. It is not equally distributed in both the groups under study.

In order for age to be a confounder,

• 1. Age must be a risk factor for the disease

• 2. Age must be associated with the exposure (but is not a result of the
exposure)
EXAMPLE OF CONFOUNDING: PANCREATIC CANCER STUDY

• In the study of whether coffee

consumption is a risk factor for Increased
coffee Drinking
pancreatic cancer, smoking is a
confounder if:
Smoking
1. It is a known risk factor for
pancreatic cancer
Increased risk
• 2. It is associated with coffee drinking of pancreatic
cancer
but is not a result of coffee drinking
APPROACHES TO THE PROBLEM OF CONFOUNDING

– In designing and carrying out the study

– Randomisation
– Matching(sampling)
– Restriction

– In the data analysis

– Stratification
– Adjustment
• Randomisation – Ideal method for ensuring potential confounding
variables are equally distributed among the groups compared.
Randomisation ensures that baseline differences between two groups
are only due to chance and the only distinction between them is the
intervention or the treatment given. The sample size should be
sufficiently large to avoid random maldistribution of variables
• Matching – Is used to control confounding by selecting study
participant so as to ensure that potential confounding variables are
evenly distributed in the two groups being compared. E.g. in case
control study of exercise and coronary heart disease, each patient
with heart disease can be matched with a control of the same age
group and sex to ensure that confounding by age and sex does not
occur.
• Restriction – It is a way to control confounding by limiting the
study to people who have particular characteristics. E.g. in a
study on the effects of coffee on coronary heart disease,
participation in the study could be restricted to non-smokers
thus removing any potential effect of confounding by cigarette
smoking.
• Stratification – Confounding can be controlled by stratification,
which involves the measurement of strength of associations in
well defined and homogenous categories (strata) of the
confounding variables. E.g. If sex is a confounder, the association
may be measured separately in men and women.
Standardisation/ Adjustment
• If the death rates of two population need to compared which
have a different age composition, the crude death death rate
cannot be used because rates are only comparable if the
populations upon which they are based is comparable. Therefore
age standardisation or age adjustment is done which removes
the confounding effect of different age strucures and yields a
single standardised adjusted rate
ECOLOGICAL FALLACY
An ecological study is one in which the units of analysis are
populations or groups of people, rather than individuals.
Gives inference on the association between exposure and outcome
at the population level (culture, religion, geography, climate, etc.)
rather than at an individual level (genes, individual behaviors)

• Eg. Study of leukemia incidence and exposure to volatile organic

chemicals in a population of a town.
Ecological fallacy is an error that could occur when an
association between variables based on group (ecological)
characteristics is used to make inferences about the association at
an individual level when such association does not exist
MEASURES OF ASSOCIATION
MEASURES OF ASSOCIATION
• QUANTITATIVE
– RR
– OR
– AR
– PAR
• QUALITATIVE- (dicussed with Hill’s criteria)
QUANTITATIVE MEASURES OF ASSOCIATION

Ratio measures
• measures of association in which relative differences between
groups being compared

Difference measures
• Difference measures are measures of association in which
absolute differences between groups being compared .
Type Example Usual application
Absolute difference Attributable Risk(AR) Primary prevention impact:
search for causes

Population Attributable Primary prevention impact

Risk(PAR)

Relative difference Relative risk/rate Search for causes

Relative odds Search for causes
(ODDS ratio)
 RELATIVE RISK
Incidence of disease among exposed Iexp
• RR = Incidence of disease among =
I non-exp
non-exposed
a/(a+b) 70/7000 LUNG CANCER
RR = = SMOKING
+ - TOTAL
c/(c+d) 3/3000
=10/1 =10 YES 70(a) 6930(b) 7000
NO 3(c) 2997(d) 3000

Lung cancer is 10 times more common in smokers than non-smokers

RR > 1 RR < 1
Risk is more in exposed Exposure is protective
(exposure is causal)
 ODDS RATIO
Also known as CROSS PRODUCT RATIO

• OR = odds of disease in exposed = Odds Exp +

odds of disease in non-exposed Odds nonExp -

(OE+) = 70/6930
OR = 70/6930 = 11.5
(OE-) = 3/2997 3/2997
Smokers are 11 times more likely to develop lung cancer
 CASE-CONTROL COHORT
How many lung cancer patients were smokers? How many smokers developed lung cancer?
DISEASE
DISEASE
+ -
+ -
SMOKING + a b
SMOKING + a b
- c d
- c d
OR = odds of lung cancer in smokers OR = odds of smokers having lung cancer
odds of lung cancer in non-smokers odds of smokers not having lung cancer
= a/b = ad = a/c = ad
c/d bc b/d bc
for eg. OR = 10 For Eg. OR = 10
Lung cancer patients are 10 times more likely Smokers are 10 times more likely to develop lung
to be smokers than those without the cancer as compared to non-smokers.
disease.
CASE CONTROL COHORT

Subjects with and without the disease Subjects with and without the exposure/
risk factor
OR RR, OR
• If the disease is rare, with a very low prevalence in the
community,
DISEASE
+ -
RISK + a b
FACTOR - c d
• OR = ad/bc
• RR = a/(a+b) a/b = ad/bc
=
c/(c+d) c/d
If, a<<<<b Therefore, RR becomes same as
c<<<<d OR when disease is rare.
 ATTRIBUTABLE RISK
Incidence of disease Incidence of disease
- among non-exposed
• AR = among exposed x 100
Incidence of disease among
exposed

= 10 -1 x 100 = 90 %
10

INFERENCE : 90% of lung cancer can be attributed to

smoking.
Atrributable risk indicates to what extent the disease
under study can be attributed to the exposure.
• Relative risk is important in assessing etiological role of a factor
in disease.
• Attributable risk is used in assessing the what proportion of the
disease incidence (both exposed & non- exposed) can be
attributed to a specific exposure
 POPULATION ATTRIBUTABLE RISK
• What proportion of the disease incidence in a total population (both
exposed & non- exposed) can be attributed to a specific exposure?
• Incidence in total population : Ipop
• Incidence in unexposed group : Ine
PAR = I - I
pop ne X 100
I pop
CAUSATION
CAUSATION
• CAUSE – A cause of a disease or injury is an event, condition,
characteristic (or a combination) which plays an important role
in producing the health outcome.
Factors in causation
• Predisposing factors
• Enabling factors
• Precipitating factors
• Reinforcing factors

Ref: R.Bonita , R.Beaglehole

PREDISPOSING FACTORS
• Predisposing factors are those that prepare, sensitize, condition,
or otherwise create a such as a level of immunity or state of
susceptibility so that the host tends to react in a specific fashion
to a disease agent, personal interaction, environmental stimulus
or specific incentive.

• Examples include age, sex, marital status, family size, educational

level, previous illness experience,
ENABLING FACTORS
• Enabling factors are those that facilitate the manifestation of
disease, disability, illhealth which favours development of
disease.
• Examples include income, health insurance coverage, nutrition,
climate, housing, personal support systems, and availability of
medical care.
PRECIPITATING FACTORS
• Precipitating factors are those associated with the definitive
onset of a disease, illness, accident, behavioral response, or
course of action. Usually one factor is more important or more
obviously recognizable than others if several are involved and
one may often be regarded as "necessary."

• Examples include exposure to specific disease, amount or level of

an infectious organism, drug, noxious agent, physical trauma,
occupational stimulus.
REINFORCING FACTORS
• Reinforcing factors are those factors which aggravate an
established disease or injury.

• Examples include repeated exposure to the same noxious

stimulus-smoking or tobacco , infectious agent, work, household,
or interpersonal environment.
MODELS OF CAUSATION
MODELS OF CAUSATION:

• – The epidemiological triad (triangle),

• – The web of causation
• – The wheel of causation
• – The sufficient cause and component causes models
• (Rothman’s component causes model)
• Counterfactual Model (Potential outcome model)
EPIDEMIOLOGICAL TRIAD
AGENT FACTORS
Physical Agents
Chemical Agents
Biological Agents
Nutritional agents

ENVIRONMENTAL FACTORS • HOST FACTORS

• Physical Environment • Socio-demographic Factors

• Biological Environment • Psycho-social Factors
• Social Environment
• Intrinsic Characteristics
WEB OF CAUSATION (MCMOHAN AND PUGH)
WHEEL OF CAUSATION (MAUSNER’S AND KRAMER’S
WHEEL MODEL)
 ROTHMAN’S COMPONENT CAUSES AND CAUSAL PIES MODEL
• Rothman's model has emphasised that the causes of disease
comprise a collection of factors.
• These factors represent pieces of a pie, the whole pie
(combinations of factors) are the sufficient causes for a disease.
• • It shows that a disease may have more that one sufficient
cause, with each sufficient cause being composed of several
factors.
• The factors represented by the pieces of the pie in this model are
called component causes.
Ref- Rothmann
• Known components (causes) – A, B,C
• Unknown component (cause) - U
A
• Necessary cause- N
• Known components causes
B
+ U
• Unknown component cause = Sufficient cause
C
+
N
• Necessary cause
 COUNTER-FACTUAL MODEL (MODEL OF POTENTIAL OUTCOME)

• In the discussion of potential outcomes, three components must be defined

• 1. A target of interest.
• 2. A list of possible interventions.
• 3. An outcome measure.
When we are interested to measure effect of a particular cause, we measure
effect in a population who are exposed.
• • We calculate risk ratios & risk differences based on this model
• • The difference of the two effect measures is the effect due the cause we
are interested in.
Ref- OTPH
 HILL’S CRITERIA
Guidelines for Judging Whether an Association Is Causal

Ref: L.Gordis
GUIDELINES FOR JUDGING WHETHER AN ASSOCIATION IS CAUSAL

• 1. Temporal relationship
• • 2. Strength of the association
• • 3. Dose-response relationship
• • 4. Replication of the findings
• • 5. Biologic plausibility
• • 6. Consideration of alternate explanations
• • 7. Cessation of exposure
• • 8. Consistency with other knowledge
• • 9. Specificity of the association
TEMPORAL ASSOCIATION
The causal attribute must precede the disease or unfavorable outcome.

Exposure to the factor must have occurred before the disease developed.

Length of interval between exposure and disease very important

For e.g. Considering a time series of measurements of exposure and effects

between high daily temperatures (> 30 degree C) and mortality during a two-
week period in Paris August 2003 revealed that there was an increase in daily
mortality during this period. This relationship between heat waves and
increased urban mortality was documented in several other cities and thus
established a temporal relationship between climate change and mortality.
STRENGTH OF THE ASSOCIATION
• The stronger the association the more likely the relationship is
causal.
• There are statistical methods to quantify the strength of
association viz; calculation of relative risk, attributable risk etc.
• For e.g. cigarette smokers have a two-fold increase of acute
myocardial infarction compared with non-smokers.
• Also the risk of lung cancer in smokers compared with non-
smokers has been shown in various studies to be increased
between four-fold and twenty-fold.
 DOSE-RESPONSE RELATIONSHIP
• As the dose of exposure increases, Age-standardised death rates due to well-
the risk of disease also increases established cases of bronchogenic carcinoma by
current amount of smoking
• If a dose-response relationship is 250

Mortality rate per 100,000 person-years

present, it is strong evidence for a 217.3

causal relationship. 200

• However, the absence of a dose- 150 143.9

response relationship does not

necessarily rule out a causal 100

relationship. 51.4
59.3
50
• For e.g. Dose response
relationship for cigarette smoking 0
3.4

and lung cancer. Never

Smoked
< 1/2 pack / 1/2 - 1 pack / 1 - 2 pack /
day day day
> 2 pack /
day
REPLICATION OF THE FINDINGS
If the relationship is causal, we would expect to find it consistently in
different studies and in different populations
• Replication of findings is particularly important in epidemiology.
• If an association is observed, we would also expect it to be seen
consistently within subgroups of the population and in different
populations, unless there is a clear reason to expect different results.

Eg. Many of the observations regarding Helicobacter pylori have been

replicated repeatedly.
More than 50 retrospective and 9 prospective studies have established
the association between smoking and lung cancer.
BIOLOGIC PLAUSIBILITY OF THE ASSOCIATION
• The association must be consistent with the other knowledge(viz
mechanism of action, evidence from animal experiments etc).
Sometimes the lack of plausibility may simply be due to the lack of
sufficient knowledge about the pathogenesis of a disease.

Eg. Although originally it was difficult to envision a bacterium that

infects the stomach antrum causing ulcers in the duodenum, it is now
recognized that Helicobacter pylori has binding sites on antral cells and
can follow these cells into the duodenum.
• Helicobacter pylori also induces mediators of inflammation.
• Helicobacter pylori-infected mucosa is weakened and is susceptible to
the damaging effects of acid.
CONSIDERATION OF ALTERNATE EXPLANATIONS
• In judging whether a reported association is causal, the extent to
which the investigators have taken other possible explanations
into account and the extent to which they have ruled out such
explanations are important considerations.

• Eg. Coffee drinking and incidence of ca pancreas (smoking is the

confounder)
 CESSATION OF EXPOSURE
• If a factor is a cause of a disease, we would expect the risk of the disease to
decline when exposure to the factor is reduced or eliminated.
When the removal of a possible cause results in a reduced disease risk, there is
a greater likelihood that the association is causal.

Eg. • Eradication of Helicobacter pylori - Long-term ulcer recurrence rates

were zero after Helicobacter pylori was eradicated using triple-antimicrobial
therapy
• In nov 1989, Withdrawal of L-Tryptophan by FDA was followed by a
dramatic reduction in the number of cases of EMS(eosinophilia-myalgia-
syndrome)
CONSISTENCY WITH OTHER KNOWLEDGE
• Consistency is the occurrence of the association at some other time
and place.
• If a relationship is causal, the findings should be consistent with other
data.

• Eg. Prevalence of Helicobacter pylori infection is the same in men as in

women. The incidence of duodenal ulcer, which in earlier years was
believed to be higher in men than in women, has been equal in recent
years.
• Studies have shown there is a consistence increase in lung cancer
rates in men and women following increased cigarette sales in men
and women.
SPECIFICITY OF THE ASSOCIATION
• An association is specific if a Specific exposure is associated with
only one disease.
• Specificity implies a one to one relationship between the cause
and effect.

Eg. Cigarette smoking can cause Ca lung, Ca pancreas, Ca bladder ,

emphysema etc.
MODIFIED GUIDELINES FOR EVALUATING THE EVIDENCE
OF A CAUSAL RELATIONSHIP
1. Major criteria
• a. Temporal relationship
• b. Biological plausibility
• c. Consistency:
• d. Alternative explanations (confounding)
2. Other considerations
• a. Dose-response relationship
• b. Strength of the association
• c. Cessation effects

Ref- L.Gordis
CORRELATION
• Measure of linear association between two variables i.e. nature &
direction of relationship.
• It indicates the degree of association between two
characteristics.
• Correlation is said to exist between two variables if changes in
the value of one variable tend to occur simultaneously with
changes in the value of another variable.
PEARSON’S SAMPLE CORRELATION COEFFICIENT, (R)

Measures relationship between two numerical characteristics

(interval data)
Measures the –
• Strength
• Direction Of association
 POSITIVE AND NEGATIVE CORRELATION {OR
ASSOCIATION}
• POSITIVE CORRELATION • NEGATIVE CORRELATION
• As the occurence of independent • As the value of independent
variable increases(or decreases), occurence increases, occurence of
occurence of dependent variable dependent variable decreases. (in
increases (or decreases opposite direction)
respectively).

Eg. 1.Female literacy and IMR

Eg- 1. smoking and lung cancer
• 2.Vaccine coverage and incidence
2. Sedentary lifestyle and NCDs of diseases

Copyright ©2004 Brooks/Cole, a division of Thomson Learning, Inc.,

modified by J. Utts, Oct 2010
BASED ON DEGREE OF CORRELATION

• Perfect positive
• Moderately positive
• Zero correlation
• Moderately negative
• Perfectly Negative

Ref- Daly and Bourke

 COEFFICIENT OF DETERMINATION r2
• r = 0.985
r2 = (0.985)^2 = 0.97
Therefore, 97% of variation in the values for one
measure, may be explained by one factor

97%

COEFFICIENT OF NON-DETERMINATION (1- r2 )

= 1- (0.985)^2 = 0.03
3 % of the variation is explained by factors other than
the factor explained.
 SPEARMAN’S RHO
• Non-parametric measure of correlation
USES -
• Ordinal data
• Numerical variables not normally distributed.

• Range from -1 to +1
• Uses ranks and not actual values
• Less sensitive to bias due to the effect of outliers.
• Used to reduce the weight of outliers, large differences get treated as a
one-rank difference.

• Does not require assumption of normality.

REGRESSION
• it is also used in measuring association. Quantifies the
association between two variables
• They are the measure of the mean changes to be expected in the
dependent variable for a unit change in the value of the
independent variable.
• When more than 1 independent variable is associated with the
dependent variable, multiple regression analysis will indicate how
much of the variation observed in the dependent variable can be
accounted for, by one or a combination of independent variables.
 BEST FIT LINE
• From the infinite number of straight lines, we select
the line to which the points in the scattergram are, in
some way, the closest.
• i.e. minimize the distance between the scatter points
and the line.

14

12
d3

Y dependent variable
10 d5

d4
6 d1
d2
4

0
0 2 4 6 8 10 12
X independent variable
 METHOD OF LEAST SQUARES
14

12
d3

Y dependent variable
10 d5

d4
6 d1
d2
4

0
0 2 4 6 8 10 12
X independent variable
 KAPPA STATISTICS
• Measure of AGREEMENT between two diagnostic
tools with none of them being the gold standard
• How much they agree with each other.
• ONE person/ procedure : intra-rater reliability
• ≥ TWO persons/ procedure : inter-rater reliability
 Statistical Inference
• Draws a conclusion about a
population based on
information from sampled
data
• Probability is used to indicate
the level of reliability in the
conclusion
• The possibility that chance,
bias, or confounding explain a
statistical association should
always be considered.
Causal Inference
• A conclusion about the
presence of a health-related
state or event and reasons for
its existence
• Causal inferences provide a
scientific basis for medium
and public health action
• Made with methods
comprising lists of criteria or
conditions applied to the
results of scientific studies
PROBLEMS IN ESTABLISHING CAUSALITY
• The existence of correlation/ association does not necessarily
imply causation.
• Concept of single cause ;concept of multiple causation
• Koch’s postulates cannot be used for non-infectious diseases.
• Specificity established in one disease does not apply on others.
PRACTICAL USES OF CAUSAL INFERENCE

• For e.g. in a discussion of the ‘Burden’ of disease due to lung

cancer
– Directly eliminating lung cancer (for e.g. how many deaths could be
prevented if we could eliminate lung cancer)
– Removing risk factor for lung cancer (for e.g. how many deaths could be
prevented if we could eliminate cigarette smoking)
– Applying an intervention to the entire population (for e.g. if we could
implement a smoking cessation program to the entire smoking
population how many deaths could be prevented)
– Applying an intervention that will produce a small change in the risk
behaviours in part of a population (for e.g. if we could implement a
smoking cessation program to the targeted group of motivated
individuals how many deaths could be prevented)
THANK U