RESEARCH VARIABLES AND

RELATIONSHIP BETWEEN
VARIABLES

Ketut Suega
Unit Litbang dan ICE-EBM
FK Unud/RSUP Sanglah
Denpasar Bali
 Definitions
• Variable: “any entity that can take on a variety of different
values” (Wrench et al, 2008, p. 104)
– gender
– self-esteem
– managerial style
– stuttering severity
• attributes, values, and levels are the variations in a variable
– Attribute: political party:
– Value: Democrat, Republican, Independent, etc.
– Attribute: Self-esteem
– Level: High, Medium, Low
 What is a Variable?

 Simply, something that varies.

 Specifically, variables represent persons or
objects that can be manipulated, controlled,
or merely measured for the sake of research.
 Variation: How much a variable varies.
Those with little variation are called
constants.
 Dependent variable

• a variable that is observed or measured, and

that is influenced or changed by the
independent variable
• dependent variables are also known as
“response” or “output” or “criterion” variables
• analogous to the “effect” in a cause-effect
relationship
 Dependent Variables

 Dependent variables are not controlled or

manipulated, but instead are simply
measured.
 Dependent Variables depend on what the
independent variable is.
 Independent Variables

 These variables are ones that are more or

less controlled.
 You might manipulate these variables as
needed.
 They still vary, but the variation is relatively
known (like seconds, or days)
 It is easy to figure the next independent
variable.
 Independent variable

• the variable that is manipulated either by the

researcher or by nature or circumstance
• independent variables are also called
“stimulus” “input” or “predictor” variables
• analogous to the “cause” in a cause-effect
relationship
 Independent Vs. Dependent

 Intentionally manipulated Intentionally left alone

 Controlled Measured
 Vary at known rate Vary at unknown rate
 Cause Effect
 Confounding variable

• also known as extraneous variables or

intervening variables
• confounding variables “muddy the waters”
• alternate causal factors or contributory factors
which unintentionally influence the results of an
experiment, but aren’t the subject of the study
 Mediating variable
• a.k.a. moderating, intervening, intermediary, or mediating
variables
• a 2nd or 3rd variable that can increase or decrease the
relationship between an independent and a dependent
variable.
• for example, whether listeners are persuaded more by the
quality or quantity of arguments is moderated by their degree
of involvement in an issue.
 Example
Time to roll down
the ramp

5 10 15 20 25
Height of a ramp (cm)
interchangeability of independent and
dependent variables
• The same concept or construct could serve as the
independent variable in one investigation, and the
dependent in another.
• example: “fetal alcohol syndrome” (FAS)
– As an independent variable: RQ: Does severity of
FAS correlate positively with language delay in
infants?
– As a dependent variable: RQ: Does the amount of
maternal alcohol use correlate positively with the
severity of FAS in infancy?
TYPE OF VARIABLES
TYPE OF VARIABLES
TYPE OF VARIABLES
TYPE OF VARIABLES
TYPE OF VARIABLES
TYPE OF VARIABLES
 Scale of Variables
• Discreetly (catagorical) • Continously (numeric)
– Nominal – Interval
– Ordinal – Ratio
 Varieties and types of variables
• Discrete variables
– Nominal variables: distinct, mutually – Dichotomous variables:
exclusive categories • true/false, female/male,
• religions; Christians, Muslims, democrat/republican
Jews, etc. – Ordered variables: mutually
• occupations; truck driver, exclusive categories, but with an
teacher, engineer order, sequence, or hierarchy
• marital status; single, married, • fall, winter, summer, spring
divorced • K-6, junior high, high school,
– Concrete versus abstract variables college
• concrete; relatively fixed,
unchanging
– biological sex
– ethnicity
• abstract; dynamic, transitory
– mood, emotion
– occupation
Varieties and types of variables--
continued
• Continuous variables:
• include constant increments or gradations, which can
be arithmetically compared and contrasted
– IQ scores
– self-esteem scores
– age
– heart rate, blood pressure
– number of gestures
 Relationships among variables
• Differences
– Differences in kind, degree
• Relationships (correlations)
– Positive correlation
– Negative correlation
– No or neutral correlation
Relationships among variables

chances
bias
confounding
causal
 If exposure X is If exposure X is
associated with outcome Applying guidelines associated with outcome
Y…..then how do we decide for Y…..then how do we
if X is a cause of Y causal inference decide if X is a cause of
Y
 Is this association causal?
• Two-stage process:

• Stage I:
– Consider alternative “non-causal explanations” for the association

• In Stage I, we ask ourselves could the association be due to:

– Bias?
– Confounding?
– Chance?

• Stage II: If the association is unlikely to be due to bias,

confounding or chance…
– ….we apply ‘guidelines’ for causal inference
 Assessing a reported association between an
exposure and an outcome in an epidemiological study
Could the observed association
be due to:

Selection or measurement
bias

No

Stage I
Confounding

No
Apply Guidelines
Chance for Causal Inference

Probably Not

Could it be causal?
Stage II
 BIAS

Systematic, non-random deviation of

results and inferences from the truth, or
processes leading to such deviation. Any
trend in the collection, analysis,
interpretation, publication or review of data
that can lead to conclusions which are
systematically different from the truth.
(Dictionary of Epidemiology, 3rd ed.)
 MORE ON BIAS
Note that in bias, the focus is on an
artifact of some part of the research
process (assembling subjects,
collecting data, analyzing data) that
produces a spurious result. Bias can
produce either a type 1 or a type 2
error, but we usually focus on type 1
errors due to bias.
 MORE ON BIAS

Bias can be either conscious or

unconscious. In epidemiology, the
word bias does not imply, as in
common usage, prejudice or
deliberate deviation from the truth.
 CONFOUNDING
A problem resulting from the fact that one feature of
study subjects has not been separated from a second
feature, and has thus been confounded with it,
producing a spurious result. The spuriousness arises
from the effect of the first feature being mistakenly
attributed to the second feature. Confounding can
produce either a type 1 or a type 2 error, but we usually
focus on type 1 errors.
 EXAMPLE OF CONFOUNDING
The mothers of breast-fed babies are of higher social
class, and the babies thus have better hygiene, less
crowding and perhaps other factors that protect against
gastroenteritis. Crowding and hygiene are truly
protective against gastroenteritis, but we mistakenly
attribute their effects to breast feeding. This is called
confounding. because the observation is correct, but its
explanation is wrong.
 THE DIFFERENCE BETWEEN
BIAS AND CONFOUNDING

Bias creates an association that is

not true, but confounding describes
an association that is true, but
potentially misleading.
 KEY PRINCIPLE IN BIAS AND
CONFOUNDING

The factor that creates the bias, or the

confounding variable, must be associated
with both the independent and dependent
variables (i.e. with the exposure and the
disease). Association of the bias or
confounder with just one of the two variables
is not enough to produce a spurious result.
Were the bias or the confounder associated
with just the independent variable or just the
dependent variable, they would not produce
bias or confounding.

This gives a useful rule:

If you can show that a potential confounder is
NOT associated with either one of the two
variables under study (exposure or outcome),
confounding can be ruled out.
 E
External Variable

Dependent Variable
Independent Variabel = dependen
= independent Mediating = efect
= predictor Variable = outcome
= risk = event
= causa = response

External Confounding
External
Variabel Variabeles Variabel

D
A

External
Variabel External
Variabel

B C
 Independent Variabel Dependent
Variabel antara Variable

A Confounding

B Independent Dependent
Variabel M Variable

Not Confounding

C Independent Dependent V
Variabel Variable
 ?
Coffee PJK

Smoking
Candy Dental carries
Snacks

Oral hygiene
CONTROLING CONFOUNDING
FACTORS

BY IDENTIFICATION
BY ELIMINATING
IDENTIFICATION

REVIEWING ARTICLES
LOGICAL
EXPERIENCE
 ELIMINATION
• ANALYTIC PROPERTIES
– STRATIFICATION
– MULTIVARIATE
• STUDY DESIGN
– RESTRICTION
– MATCHING
– RANDOMIZATION
Dr. Yoga Nathan
Senior Lecturer in Public Health
GEMS UL
“In what circumstances can we pass from an observed association to a
verdict of causation? Upon what basis should we proceed to do so?”

Nine ‘aspects of an association’ should be considered before

deciding that the most likely interpretation is causation
Aspects of an association that should be considered
when inferring causality

 Strength  Plausibility

 Consistency
 Coherence

 Specificity
 Experimental
evidence
 Temporality

 Dose-response  Analogy
 Consistency
• Repeated observation of an association in studies conducted on
different populations under different circumstances
• If studies conducted by….
– different researchers
– at different times
– in different settings
– on different populations
– using different study designs
……all produce consistent results,
this strengthens the argument for causation
Epidemiological studies (1 - 14)

study
 Consistency
• Repeated observation of an association in studies conducted on
different populations under different circumstances
• If studies conducted by….
– different researchers
– at different times
– in different settings
– on different populations
– using different study designs
……all produce consistent results, this strengthens the argument for
causation

• e.g. The association between cigarette smoking and lung cancer

has been consistently demonstrated in a number of different
types of epidemiological study (ecological, case-control, cohort)
 Is there a causal relationship
between fluoride in water and bone fractures?
• 18 studies have investigated the association between hip
fractures (outcome) and water fluoride level (exposure)
– 30 separate statistical analyses
• 14 analyses produced a ‘positive association’
• 13 analyses produced a ‘negative association’
• 3 ‘no association’
The inconsistency of these results casts doubt on the hypothesis
that there is a causal relationship between fluoride in water and
bone fractures
Is there a causal relationship between fluoride in water and bone
fractures?
• 18 studies have investigated the association between
hip fractures (outcome) and water fluoride level
(exposure)
– 30 separate statistical analyses

• 14 analyses produced a ‘positive association’

• 13 analyses produced a ‘negative association’
• 3 ‘no association’

• The inconsistency of these results casts doubt on the

hypothesised causal relationship between fluoride in
water and bone fractures
 Oral Contraceptive Use and
Ovarian Cancer
-ve Association + ve Association
Hospital-Based

Hildreth et al, 1981

Case-Control

Rosenberg et al, 1982

La Vecchia et al, 1984
Tzonou et al, 1984
Booth et al, 1989
Hartge et al, 1989
WHO, 1989
Wu et al, 1988
Prazzini et al, 1991
Newhouse et al, 1977
Community-Based

Casagrande et al, 1979

Case-Control

Cramer et al, 1982

Willet et al, 1981
Weiss, 1981
Risch et al, 1983
CASH, 1987
Harlow et al, 1988
Shu et al, 1989
Walnut Creek, 1981
Cohort

Vessey et al, 1987

Beral et al, 1988

0.0 0.5 1.0 1.5 2.0 2.5 3.0 3.5

Relative Risk or Odds Ratio
Hankinson SE et al. Obstet Gynecol. 1991;80:708-714.
www.contraceptiononline.
 Oral Contraceptive Use and
Ovarian Cancer
-ve Association + ve Association
Hospital-Based

Hildreth et al, 1981

Case-Control

Rosenberg et al, 1982

La Vecchia et al, 1984
Tzonou et al, 1984
Booth et al, 1989
Hartge et al, 1989
WHO, 1989
Wu et al, 1988
Prazzini et al, 1991
Newhouse et al, 1977
Community-Based

Casagrande et al, 1979

Case-Control

Cramer et al, 1982

Willet et al, 1981
Weiss, 1981
Risch et al, 1983
CASH, 1987
Harlow et al, 1988
Shu et al, 1989
Walnut Creek, 1981
Cohort

Vessey et al, 1987

Beral et al, 1988

0.0 0.5 1.0 1.5 2.0 2.5 3.0 3.5

Relative Risk or Odds Ratio
Hankinson SE et al. Obstet Gynecol. 1991;80:708-714.
www.contraceptiononline.
“….to our knowledge no other data on the
association between preschool diet
and breast cancer are available”
(Michels et al., 2006: 751)
 Strength of the association
• “Measures of association”
– used to quantify the strength of the association between an
exposure and outcome
– e.g. Relative risk, odds ratio

• Strong associations are more likely to be causal than

weak associations
– The larger the relative risk (RR) or odds ratio (OR), the greater
the likelihood that the relationship is causal

• Weak associations are more likely to be explained by

undetected biases or confounders
 Strength of the association
• How large must a relative risk or odds ratio be to be
considered ‘strong’:
– 2 ? 4 ? 20 ? …..?

• No universal agreement regarding what constitutes a

‘strong’ or ‘weak’ association
– An OR or RR > 2.0 is ‘moderately strong’
– An OR or RR > 5.0 is ‘strong’

• The relationship between smoking and lung cancer is

an excellent example of a ‘strong association’
– odds ratios and relative risks in different studies are in the 4
to 20 range
“For one additional serving of French Fries
per week, the odds ratio for breast cancer
was 1.27” (Michels et al., 2006)

i.e. a “weak association”

 Temporality
• This refers to the necessity for the exposure to
precede the outcome (effect) in time
• Any claim of causation must involve the cause
preceding in time the presumed effect
• Easier to establish in certain study designs
– Prospective cohort study
Easiest to establish in a cohort study. Lack of temporality rules out
causality

Outcome
Exposure TIME Normal Cancer
lung
 Temporality – British Doctors Cohort Study
Lung Ca.
• This refers to the necessity for the exposure to
precede the outcome (effect)Smokers
in time no
Lung Ca.
• Any claim of causation must involve the cause
Lung Ca.
preceding in timeBritish
40,634 the presumedExeffect
Population Doctors Smokers
no
• Easier to establish in certain study designsLung Ca.
– Prospective cohort study
Lung Ca.
Non
Lack of temporality rules out causality
Smokers no
Lung Ca.
Time
Exposure TIME Outcome
 Temporality
• This refers to the necessity for the exposure to
precede the outcome (effect) in time
• Any claim of causation must involve the cause
preceding in time the presumed effect
• Easier to establish in certain study designs
– Prospective cohort study

• Lack of temporality rules out causality

Exposure TIME Outcome

 Dose-response relationship
• Dose-response (‘biological gradient’)
– the relationship between the amount of exposure (dose) to a
substance and the resulting changes in outcome (response)

• If an increase in the level of exposure increases the risk

of the outcome
– this strengthens the argument for causality
R
R I
R I S
R I
I
S
S K
S
K K K
0 cigs/day < 5 cigs/day 5 - 20 cigs/day > 20 cigs/day
 Dose-response relationship
Dose-Response

Percentage of people with hearing loss

relative to workplace noise exposure
Average noise level
during an 8-hour Exposure time (years)
working day
(decibels) 5 10 40
<80 0 0 0
85 1 3 10
90 4 10 21
95 7 17 29
100 12 29 41
105 18 42 54
110 26 55 62
115 36 71 64
 (Biological) Plausibility

• Plausibility refers to the biological

plausibility of the hypothesised
causal relationship between the
exposure and the outcome
– Is there a logical and plausible biological mechanism
to explain the relationship?
“A high dose of caffeine could constrict a mother’s blood vessels
reducing the blood flow to the placenta” (Biological Plausibility)

< 200 mg caffeine/day

 “There is no accepted biological
mechanism to explain the
epidemiological results; indeed the
relation may be due to chance
or confounding”
(Draper et al., 2005)
 Biological plausibility
But other researchers have argued that there
is a biologically plausible explanation……..
• EMF can induce currents that might alter the voltages
across cell membranes
• Magnetic fields might cause the movement of
ferromagnetic particles within cells

• EMF fields might also influence free radicals

Power lines might deflect and concentrate cosmic rays on

people living within their vicinity
 Biological plausibility
It is generally easy to ‘manufacture’ biologically
plausible explanations for the findings from
epidemiological research
Biological plausibility is not a particularly useful
viewpoint for assessing a causal relationship
 STUDY DESIGN
Relative ability of different types of
study to ‘prove’ causation
NB: Assuming study well-designed & conducted & bias etc. minimised

Type of Study Ability to ‘prove’

causation
1) Randomised STRONG
Controlled Trial
2) Cohort Study Moderate
3) Case-control study Moderate
4) Cross-sectional study WEAK
5) Ecological study WEAK
 Is this association causal?

Does consumption of French fries by preschool

children cause breast cancer?
Strength
Consistency
Temporality
Dose response
Biological plausibility
Study design
 Is this association causal?

Does consumption of French fries by preschool

children cause breast cancer?
Strength Weak: OR = 1.27
Consistency No
Temporality Yes
Dose response No
Biological plausibility Yes
Study design Case Control
Is this association causal?
 Is this association causal?

Does consumption of French fries by preschool

children cause breast cancer?
Strength Weak: OR = 1.27
Consistency No
Temporality Yes
Dose response No
Biological plausibility Yes
Study design Case Control
Is this association causal?
 Is this association causal?

Does cigarette smoking cause lung cancer?

Strength Strong: OR, RR = 4 - 20
Consistency Yes
Temporality Yes
Dose response Yes
Biological plausibility Yes
Study design Ecological, C/S, CC, Cohort

Is this association causal?

 Is this association causal?

Does cigarette smoking cause lung cancer?

Strength Strong: OR, RR = 4 - 20
Consistency Yes
Temporality Yes
Dose response Yes
Biological plausibility Yes
Study design Ecological, C/S, CC, Cohort

Is this association causal?

 If exposure X is If exposure X is
associated with outcome Applying guidelines associated with outcome
Y…..then how do we decide for Y…..then how do we
if X is a cause of Y causal inference decide if X is a cause of
Y
Sir Bradford Hill established the following nine criteria for
causation (does factor A cause disorder B). Although
developed for use in the field of occupational medicine,
these criteria can be used in most situations.

• Strength of the association. How large is the effect?

• The consistency of the association. Has the same
association been observed by others, in different
populations, using a different method?
• Specificity. Does altering only the cause alter the effect?
• Temporal relationship. Does the cause precede the
effect?
• Biological gradient. Is there a dose response?
• Biological plausibility. Does it make sense?
• Coherence. Does the evidence fit with what is
known regarding the natural history and biology
of the outcome?
• Experimental evidence. Are there any clinical
studies supporting the association?
• Reasoning by analogy. Is the observed
association supported by similar associations?
 In the following example, we apply Hill’s criteria to the
classic case of smoking and lung cancer.

• : Strength of Association. “The lung cancer rate

for smokers was quite a bit higher than for non-
smokers (e.g., one study estimated that smokers
are about 35% more likely than non-smokers to get
lung cancer)”.
• 2: Temporality. Smoking in the vast majority of
cases preceded the onset of lung cancer
• Consistency. Different methods (e.g.,
prospective and retrospective studies)
produced the same result. The relationship
also appeared for different kinds of people
(e.g., males and females)
• Theoretical Plausibility. Biological theory of
smoking causing tissue damage which over
time results in cancer in the cells was a
highly plausible explanation
Coherence. The conclusion (that
smoking causes lung cancer) “made
sense” given the current knowledge
about the biology and history of the
disease
Specificity in the causes. Lung
cancer is best predicted from the
incidence of smoking
• Dose Response Relationship. Data showed a
positive, linear relationship between the amount
smoked and the incidence of lung cancer.
• Experimental Evidence. Tar painted on laboratory
rabbits’ ears was shown to produce cancer in the ear
tissue over time. Hence, it was clear that carcinogens
were present in tobacco tar.
• Analogy. Induced smoking with laboratory rats
showed a causal relationship. It, therefore, was not a
great jump for scientists to apply this to humans
 When using them, don’t forget Hill’s
advice:
• “None of these nine viewpoints can bring
indisputable evidence for or against a cause
and effect hypothesis …. What they can do,
with greater or less strength, is to help answer
the fundamental question—is there any other
way of explaining the set of facts before us, is
there any other answer equally, or more, likely
than cause and effect?” (Cited in Doll, 1991).
 MATUR
THANK YOU SUKSMA TERIMAKASIH