BIOSTATISTICS

Variables and Types

Data and Sources of Data
Methods of Data Collection
Variable:

 A variable is a characteristic or attribute that

takes on different values in different persons,
places, or things.

For Example
• heart rate,
• the ages of patients seen in a dental clinic
• the weights of preschool children
• the number of daily admission in a hospital
• level of protein in blood.
Types of Variables:

 Quantitative Variables:

 The variables that can be measured in the

usual sense

 Qualitative Variables:

 Many characteristics are not capable of

being measured directly. Some of them can
be ordered (Ordinal) Some of then cannot be
ordered (Nominal)
  Quantitative variables

There are two types of quantitative variables –

discrete or continuous

 A discrete variable takes only exact values

such as family size and patients admission.

 A continuous variable is the one which takes

any value between a specified range: such as
age and height
 Qualitative variables

 Qualitative variables are almost invariably

discrete as they have a limited number of categories
such as parts affected: liver, kidney, heart etc.

 When only two categories are applied

(recovered / not recovered, and male / female), the
measurement is binary ( binary variable will take
only two values - the presence of liver disease –
ether yes (1) or no (0).
Scales of Measurement
 The calibration used for any measurement –
qualitative or quantitative – is called the scale.

 Variables can be classified by scale of

measurement as:
 Nominal
 Ordinal
 Numeric (metric or scale)
 Ratio
 Interval
  Nominal
 Variable consists of named categories with no
implied order among them.

• Gender (M, F)
• Location of tuberculosis (lung, bone or abdomen)
• Complaints (pain, vomiting, constipation)
• Blood Group (A, B, O or AB)
• Color of eyes (blue, green, brown, black)
• Exam result (P, F)
• Received treatment or did not (R, NR)
• Has cancer or not (C, NC)
 Is coded, but has no quantitative value
• (Male: 1, Female: 2)
 Ordinal
 Variable consists of ordered categories and
differences between categories are not equal.
• Patient status (Improved / Same / Worse)
• Diagnosis (Stage I / Stage II / Stage III)
• Severity of injury (Mild /Moderate /Serious
/Critical)
• Severity of disease (Mild / Moderate / Severe)
• Income status (Low / Middle / High)
• Evaluation (Satisfied / Neutral / Dissatisfied)

 The coding now has meaning

• Improved = 2, Same = 1, Worse = 0 (However the

distance between values is not a constant.)
 Numeric / Metric: Interval

 Variable has equal distances between values

but the zero point is arbitrary.
• For examples: IQ, Temperature
• Temperature (37ºC-36ºC; 38ºC-37ºC are equal)
but no implication of ratio (30ºC is not as twice hot
as 15ºC). Even for weather, 0ºC does not mean
no temperature.
• IQ (70 to 80 same as IQ 90 to 100) but no
implication of ratio, and IQ scale could convert to
100 – 500 and have same meaning. (IQ of 100 is
not twice as smart as IQ of 50)
  Numeric / Metric: Ratio
 Variable has equal intervals between values
and a meaningful zero point.

• For examples: age, weight, height, family size,

pulse rate,
• 220 pounds is twice as heavy as 110 pounds.
Even when converted to kilos, the ratio stays
the same (100 kilos is twice as 50 kilos)
• Person with weight of 80 kg is twice as heavy
as the one with weight 40 kg.
• Pulse rate of 120 is twice as fast as 60
• Age 30 years is triple of age 10 years
Common Notations:
For Population and Sample Values
Summary Population Sample
Parameter Statistics
Mean 
x
Standard Deviation  s
Variance  s2

Proportion P p
Complement of Q q
proportion
Data and Types

 Data are raw materials of statistics. Data refers

to the set of values of one or more variables
recorded on one or more observational units.

 We may define data as figures (numbers,

observations) usually obtained by some process
of counting or measurement

 It is the outcome of facts (sex, occupation etc.),

events (birth, death, disease etc), or measurements
(height, weight etc) about many individuals.
 Data

Qualitative Data Quantitative Data

Nominal Data Ordered Data Numeric Data

Discrete data Continuous data

Interval Ratio
Sources of Medical Data

We search for suitable data to serve as the raw

material for our investigation. Such data are available
from one or more of the following sources:

1. Routinely Kept Records

Organizations keep records of their day to day

operations. For example, the hospital medical
records contain immense amounts of information on
patients. The hospital accounting records contain a
wealth of data on the facility’s business activities
2. Survey

The source may be a survey if the data needed is

about answering certain questions or issues, As
for example, If the administrator of a clinic wishes
to obtain information regarding the mode of
transportation used by patients to visit the clinic,
then the survey may be conducted among
patients to obtain this information.
3. Experiments:

Frequently the data needed to answer a

question are available only as a result of an
experiment. For example, If a nurse wishes to
know which of several strategies is best for
maximizing patient compliance, she might
conduct an experiment in which the different
strategies of motivating compliance are tried with
different patients.
4. External sources:
The data needed to answer a question may already
exists in the form of published reports, commercially
available data banks, or the research literature, i.e.
some one else has already asked the same
question. The books, journal, internet, research
publications etc are external sources. External
sources may have published or unpublished data.
The published sources are easily available. The
data are also available from MoHP /DoHS, NHRC,
Hospital and Health Centers.
Primary and Secondary Sources of Data

 Primary Data are those fresh and original

data which are collected and recorded by the
investigator or researcher. They are the first hand
data. Primary data are collected for specific
purpose of study of investigator or researcher..
The sources for this type of data is called
primary sources.
The methods of collecting primary data are:
 Direct Personal Interview
 Indirect Personal Interview
 Information through correspondence
 Mailed Questionnaire
 Schedule sent through enumerators
 Secondary data refers to information that has
previously been gathered by someone other
than the researcher and / or for some other
purpose than the research project at hand.
 The secondary data are collected through
reports and publication from Ministry of health,
Central Bureau of statistics, UNDP, WHO,
ADB, World Bank,etc
.The secondary medical data can be
assessed through websites like Pubmed,
Hinary, Medline etc
.Suitability, Reliability and Adequacy are the
points to be considered before using
secondary data.
Methods of Data Collection

Interviewing or Enumeration

 directly asking questions – history taking of

patients is a part of medical process
 information collected by face to face dialogue

 success depend on the rapport established

between interviewer and respondent
 ability of interviewer to extract information

 readiness of the respondents

Questionnaire, Schedule and Proforma

 Questionnaire consists of series of structured

questions. Schedule comprises a list of items on
which the information is to be collected.
Proforma is just a format, which is suitable., for
example, for heading in a register on which the
information is recorded.
Note the following !!!

 Questionnaire - to be standardized and

pretested
 Quality of questionnaire
 Enthusiasm of respondents, ability of
respondents to give accurate information
 Information about large number of attributes
and verities can be collected in short times
Examination, Investigation and Experimentation

 Examination of patients in most intimate

manner
 Clinical signs and symptoms

 Radiological and laboratory investigation

 Disease specific special tests

 Required information is collected by actual

measurement
Observations
 observing the respondents indirectly to obtain
information - people washing hands before
taking meals

Records
 information required can be available in
various records like hospital records, census or
survey records, service records etc.
 The utility of information depends on its
uniformity, completeness, standardization,
accuracy, and the reasons for which the
information was collected.