VARIABLE

Anything that can vary

along some dimension. This
means that it must have
more than one value or level
e.g. “sex of subject” is a
variable as it has two values
i.e. male and female.
 A Variable is a characteristic of a
person, object or phenomenon that
can take on different values.

A simple example of a variable is a

person’s age. The variable age can
take on different values because
a person can be 20 years old, 35
years old, and so on.
Other examples of variables are

– Weight (expressed in kilograms or in

pounds);
– Distance between homes and clinic
(expressed in kilometers or in minutes
walking distances
– Monthly income ( expressed in dollars,
rupees,or Kwachas.)
– Because the values of all these variables are
expressed in numbers, we call them
Numerical Variables.
 The different values of a variable may also be
expressed in categories. For example, the variable
sex has two values, male and female, which are
distinct categories. Other example are:

VARIABLES CATEGORIES
Colour Red
Blue
Green etc.
Outcome of disease Recovery
Chronic illness
Death
Since the value of these variables are expressed in categories, we
call them CATEGORICAL VARIABLES.
 Variables

Dependent Variables Independent Variable

Confounding Variable
Dependent and independent variables
Because in health system research you often look
for causal explanations, It is important to make
distinction between dependent and independent
variables.
The variable that is used to describe or measure the
problem under study is called the DEPENDENT
variable.
The variables that are used to describe or measure
the factors that are assumed to cause or at least to
influence the problem are called the INDEPENDENT
variables.
 For example, in a study of the
relationship between smoking and
lung cancer, “suffering from lung
cancer”(with the values yes, no )
would be the dependent variable
and “smoking” ( varying from not
smoking to smoking more than
three packets a day) the
independent variables.
The statement of the problem and the objectives

of the study determine whether a variable is

dependent or independent. It is, therefore,

important when designing a study to clearly

state which variable is the dependent and which

are the independent ones.

If a research investigates why people smoke,

“smoking “is the dependent , and “pressure

from peers to smoke”could be an independent

note that in the lung cancer study “smoking “

was the independent variable.

Although in everyday language we may speak of possible

CAUSES of problems, in scientific language we prefer to

speak of ASSOCIATIONS between variables, unless a

casual relationship can be proven If we find an

association between smoking and cancer,we can conclude that

smoking causes cancer only if we can both demonstrate that the

cancer was developed after the patient started smoking

and that there are no other factors that may have caused both
the cancer and the habit of smoking. Nervous people, for
example, may both smoke more and suffer more from cancer,
than persons who are not nervous.
Certain variables may produce changes in
the DV which are mistakenly interpreted as
representing effects of the IV. When this
happens, the variable is called a
confounding variable because its effects are
confused with IV effects.

A variable that is associated with the

problem and with a possible cause of the
problem is a potential CONFOUNDING
VARIABLE.
 A confounding variable may either strengthen
or weaken the
apparent relationship between the problem and
a possible cause.

Cause Effect/outcome
(independent variable) (dependent
variable)

Other factors

(confounding variables)
Therefore, to give a true picture of cause
and effect, the confounding variables
must be considered, either at planning
stage or while doing data analysis.

For example:
A relationship is shown between the low
level of the mother’s education and
malnutrition in under--5’s However, family
income may be related to the mother’s
education as well as to malnutrition.
Mother education Malnutrition
(independent variable) (dependent
variable)

Family income
confounding variable)
 Family income is therefore a potential

confounding variable. To give a true picture

of

the relationship between mother’s education

and

malnutrition, family income should also be

considered and measured.

 This could either be incorporated into the

research design, for example by selecting mothers

with a specific level of family income, or it can be

taken into account in the analysis of the findings,

with mother’s education and malnutrition

among their children being analyzed for families

with different categories of income.

Confounding
The concept of confounding is a central
one in the interpretation of any
epidemiological study.
Confounding can be thought of as
mixing of the effect of the exposure
under study on the disease with that of
an extraneous factor.
This external factor (other than the
exposure and the disease under study)
must be associated with the exposure
and,independent of the exposure must
be a risk factor for the disease.
Situation in which ‘F’ is a confounder
for a disease -exposure association.
Smoking MI

age

botfd Diarrhea

bad sanitation
 Table 1. Relation of Myocardial infarction
(MI)to Recent Oral Contraceptive (OC) Use.

MI Control Estimated
relative risk
OC
Yes 29 135 =1.68
No 205 1607
Total 234 1742
Source: Shapiro et al. 1979.
age- use specific relative
risk

25-29 Yes 04 62 7.2

No 02 224

30-34 Yes 09 33 8.9

No 12 390
35-39 Yes 04 26 1.5

No 33 330

40-44 Yes 06 09 3.7

No 65 362
45-49 Yes 06 05 3.9
No 93 301
Total 234 1742
 Confounding can be controlled in
study design through:
Restriction
Matching exposure

Randomization of
Confounding can be controlled in analysis
through:

Stratification
Multivariate analysis
 have to

be evaluated in several clinical trials and

other

epidemiological investigation where

appropriate

selection of the population to be studied is

made

and with proper study design, so that the

results

can be applied to other population I.e., they

are
 Research studies and variables:

Experiments and research studies are

designed

around variables. Variables are measured,

variables are manipulated by the researcher

to

see how they affect other variables. Two or

more

variables are measured at the same time to

see if
 CHARACTERISTICS OF DIFFERENT
TYPES OF MEASUREMENT:
1- A measure scale must consist of at
least two different possible
measurement categories or
values.
2- The usable scale of measurement
should be complete or
exhaustive i.e. Muslim,Hindus,etc.
3- The measures we define along our
scale of measurement should be
mutually exclusive.
 SCALE OF MEASUREMENT:

A scale of measurement is defined

before

any observation is done or any

measurements are taken by the

experimenter.
Measures vary from crude to
precise:
Some aspects of person such as
height, age

or income can be measured in a very

precise fashion,other aspects such an

attractiveness of appearance do not

lend
 TAKING MEASURES
“ I have met a wonderful young man.

He is handsome, six footer with

engaging

smile,long brown hair and a guitar.

If a measurement scale has:
• (I) two or more possible measures.

• (ii) is exhaustive so that each and every

subject can be assigned.

• (iii) Is mutually exclusive, so that no

subject can be assigned two different
measures on the same scale.
 It is nominal scale e.g. Sex is a
;nominal scale.
However, if in addition to above, the
scale also has a natural order, then the
scale is ordinal.
And if the scale also has equal sized
steps, then the scale is an interval
scale only measures assigned
according to an interval scale can be
added and subtracted.
 ORDINAL SCALES OF MEASUREMENT:

The measurement scale may possess

ordered categories but the possible

measures along the scale may not be

truly

equidistant.
 Strongly Disagree
Disagree agree NEGATIVE

Mildly disagree

No opinion NEUTRAL

Mildly agree
Agree POSITIVE

Strongly agree
 Designing an experiment:

The design of a research project is the

overall

plan for how the research will be

performed.

When you develop your design you have to

specify how many IVs you are going to

investigate and how many levels of each IV

you

intend to use..
Your design determines how you will sort
your

subjects into groups and how many groups

you

will need. Your design must specify when

and

how often you will take measures on your

DVS
ASSOCIATION AND CAUSATION
 Association refers to the statistical
dependence

between two variables I.e., the degree to which

the

rate of a disease is higher or lower with a

specific

exposure than the rate of disease among those

without the exposure.

 But the presence of Association does not
imply

that the relationship between the variables

is one

of cause and effect.

Primary objective of a researcher is to judge

whether an association between exposure

and

disease is causal.
 The judgement about an association
rests on two elements:
That the association is:
Valid: Look for alternative explanations
including, confounding, chance and
bias.

Repeatable: the evidence taken from a

number of sources supporting the
judgement of causality.
Chance
Evaluation of the role of chance
consists of two components:-
Hypothesis testing: performing a test
of statistical significance with the p-
value to determine the likelihood that
sampling variability can be
considered as an explanation.
Estimation of the confidence
interval:to indicate the range within
which the true estimate of effect is
likely to have with a given degree of
assurance.
BIAS
 Any systematic error that results
in an incorrect estimate of the
association between the exposure
and disease outcome. Usually
introduced by the experimenter or
the researcher himself due to non-
standardized measuring
techniques.
Type of Bias:-
Selection Bias
Observation/Information Bias:-
Recall Bias
Interviewers Bias
Lost-to-follow up
Misclassification
Can Control Bias:-

In study design

Choice of study population

Data collection:-
Questionnaire
Instruments
Blinding
Standardization of instruments
Source of information.
Risk factors:
Are ascertainable characteristics or circumstances of a
person or group of persons AND are associated with a
disease outcome.
* They have a temporal relationship with the
disease outcome.
* One or a combination of factors will increase the
risk
* They are statistically associated with a disease
outcome.
* They may have casual relationship with a
disease outcome but are not the cause of
a disease.
* Removal of a risk factor may decrease the risk
of a disease outcome.
Risk:
Is defined as the probability of an

adverse consequence/s in the

presence

of one or more characteristic/s or

factors.