INTRODUCTION TO

BIOSTATISTICS

1
By
Sumaira Naz
BScN, MPH
OBJECTIVES
At the end of lecture students will understand what
is….
Statistics & bio-statistics?
Descriptive &inferential statistics?
Population & sample?
Parameter & statistic?
Data & variable?
Types of data & types of variables?
Scales of measurements?

2
WHAT IS STATISTICS?
The science of data involves:

Collection of information
Classification of information
Summarization of information
Organization of information
Interpretation of information
If related to Biological or Medical sciences called Bio-
statistics
Statistics is a body of techniques and procedures dealing
with the collection, organization, analysis, interpretation
and presentation of information that can be stated 3

numerically.
THE WORD STATISTICS ALSO
REFERS TO:
The recorded data such as number of traffic
accidents, the size of enrollment, or the
number of patients visiting a clinic

The characteristics calculated for a data set,

for example average household size,
prevalence of smoking, infant morality rate,
crude death rate, immunization coverage
among children
(< 5 years), percent use safe water etc.
4
WHY DO WE NEED TO STUDY
BIOSTATISTICS COURSE?

Statistics has widespread use in health sciences, so

there is need for all health professionals to learn Bio-
statistics par ticularly those who are involve in
research. It help research:
To le ar n ho w t o d e al w it h num b e r s, alt ho ug h
computers makes these calculations easier, but so
not replace the need to understand the methods.
To assess evidence from different studies
To understand published scientific papers
To do research and write papers in scientific journals.

5
TYPES OF STATISTICS:

Descriptive vs. inferential statistic

1. Descriptive statistics: Descriptive statistics
includes statistical procedures that we use to describe
the population we are studying.
Descriptive statistics can only be used to describe the
group that is being studying. That is, the results cannot
be generalized to any larger group.
Frequency distributions, measures of central tendency
(mean, median, and mode), and graphs like pie charts
and bar charts that describe the data are all examples
of descriptive statistics.
 Example:
Of descriptive statistics is decennial censes of united
states, in which all the resident are requested to
provide information such as age, sex, race, and
marital status. The data obtained in such a scenes
can then be compiled and arranged into tables and
graphs.

7
2. Inferential statistics: Inferential statistics is
concerned with making predictions or inferences
about a population from observations and analyses
of a sample.
That is, we can take the results of an analysis using
a sample and can generalize it to the larger
population that the sample represents.
To address this issue of generalization, we have
tests of significance. A Chi-square or T-test, for
example, can tell us the probability that the results of
our analysis on the sample are representative of the
population that the sample represents

8
Example: of inferential statistics is an opinion poll
such as the Gallup Poll.
In which an attempt will draw inference to the out
come of an election. In such poll a sample of
individual (frequently less then 2000) is selected,
their preferences are tabulated and an inference is
made as to how more than 80 million people would
vote if an election will held.

9
POPULATION VS. SAMPLE
Population
 The se t o f all me asure me nts o f inte re st to the
investigator.
 It varies with the problem or situation
Example of population

Monthly income of households in Pakistan

Households in Karachi who have death of at least one
family member in past one year
Number of TB Patients in Pakistan
All patients came to certain clinic in the year 2004
10
Sample
 Any subset of all measurements selected from the
population.
 A ra nd o m sa m pl e i s a go o d re pre se nt a t i v e o f
population
 A census includes all population members in also an
example of sample.

EXAMPLES OF SAMPLE
A survey of 1,000 households taken from all parts of
Pakistan to assess their monthly income
A survey of 500 households conducted in Karachi to know
whether the have death of at least one family member in
past one year
A survey of 2500 TB patients conducted at different TB
clinics in Pakistan 11
DEFINE POPULATION FOR EACH
OF THE FOLLOWING STATEMENT?
More than 1 in 4 united state children (<5years)have
cholesterol levels of 180 milligrams or higher (source: The
American Health Foundation)

When older people (65 years and above) with mild to

moderate hypertension in Canada where given the mineral
salt for six months, the average blood pressure reading
dropped by eight points systolic and three points diastolic
(source: prevention, March 1995, p. 19)

12
PARAMETERS VS. STATISTIC
Parameters :
 Is the characteristics / set of measurements in a population
may be summarized by a descriptive characteristic e.g.
average household size and percent of households with modern
sanitation as reported in the 1998 census of Karachi

Statistic :
• when the same characteristics pertains to the sample it
is called statistic.
 The set of measurements in a sample may be summarized by a
descriptive characteristic e.g. average household size and
percent of households as reported from a sample survey of
6,000 households in Karachi, 2001
13
EXAMPLE OF PARAMETER
Average monthly income of households in Pakistan
Proportion of households in Karachi who have at least
one special child at their residence
Prevalence of TB in Pakistan

Note : If taken from a sample each one of above is called

Statistic

14
VARIABLE AND DATA
Variable :
 Characteristic or property of an individual population unit.
 T h e valu e of ch aracteristic may very amon g u n its in a
population
Data :
 The values of observations recorded for variables

15
WHAT IS DATA?

 DATA (Latin : Datum)

 the collection of information in numerical form

 It is of two types:

 1. Qualitative or Categorical data (sex, Color,

Race)
 2. Quantitative or Nominal data (Age, Height,
Parity etc)
QUANTITATIVE VS. QUALITATIVE
Quantitative Data (Measurement/numerical) :
 Data that are measure on a naturally occurring
numerical scale
Qualitative Data (Categorical)
 Data that cannot be measured on a natural occurring
numerical scale.
 Can only be classified into a group of categories
(classes)

17
EXAMPLES OF
Qualitative Data Quantitative Data
Severity of pain (mild Height (in cm)
moderate, or sever) Weight (in Kg)
Level of education (illiterate, Age (in year)
can read or write, primary,
secondary, metric, Year of Schooling
intermediate, graduate post Duration of disease
graduate) I Q of a person
Major causes of deaths in Number of children
developed countries Grade points
Sex (Male, Female) (0,1,2,3,4)
Medical Record number
Grades (A,B,C or D)
Nationality (Pakistani, Afghani 18
etc)
Passport Number
TYPES OF DATA ON THE BASIS OF SOURCE:
 The data to be collected are generally of two types.

 Primary Data.
 Secondary Data.

 Primary Data
 Collected directly from the field of inquiry
 Collected for a specific purpose
 Information provided is detailed, complete and to the point

 Primary data sources: are obtained from the original data

source. That is, documentation in the patient’s
medical/health record collected by staff at either a hospital,
clinic or aid post. Daily ward census reports collected in
hospitals are also primary data.
CONT…....
2. Secondary Data
• Data collected for another purpose by another agency
• Contain unnecessary information
• Cost effective
• Already analyzed

• Secondary data sources:

Data sets derived from primary data Secondary data are
individual or aggregate health care data found in reports that
are summarized from the source. At the hospital or health
center level, secondary data include:

The master patients’ index, disease and procedure indexes,

health care statistics and disease registries. At primary care
level, they also include patients’ name index and statistics.
PROCEDURE FOR DATA COLLECTION
Natural observation :
 Go out into the field and observe phenomena (People, animal),
and if possible without interfering with the phenomena itself
Survey
 It is also kind of observational study. You are just collecting
information without having any control

21
PROCEDURE FOR DATA
COLLECTION (CONTD.)
Case study :
 One unusual individual is intensively studies

Experiment :
 Where one variable is deliberately manipulated. It is a kind of
research plan that have another group called controls.

22
IDENTIFY AS A SURVEY OR AN
EXPERIMENT?
Canc e r re se arc h i nsti tute i s i nte re ste d i n
determining the effectiveness of a new drug for
the treatment of cancer.
The cardio-vascular department is interested in
knowing the prevalence of Rheumatic heart
disease ( RHD) in rural and urban areas of
Pakistan.
The Goldberger and his colleague’s trail studying
dietary etiology and prevention of pellagra. They
studied the effect of protective diet in two
orphanages and two wards of state mental
institutions. They used one of each type for
dietary intervention and the other served as
control.
23
VARIABLES
Variables are characteristics associated with
the subjects of the study. Height, weight,
plasma cholesterol, gender and occupation
are all variables.

Variables are so called because they tend to

vary between subjects.

Variables are grouped into quantitative and

qualitative variables.
VARIABLES

Discrete
Quantitative

Variables Continuous
Ordinal
Qualitative Dichotomous

Nominal
 TYPES OF VARIABLES
Variable Type

Categorical Numerical
(Qualitative) (Quantitative)

Nominal/Unordered Ordinal/Ordered Discrete Continuous

categorical categorical (1,2,3) (1.20, 1.35)

-Age group
-Nutritional status Number of
Income weight
e.g. Gender; people in
-Social class height distance
male, female Household
-Level of (in decimals)
blood group (whole Nos.)
knowledge
food type A,O,B,AB
e.g. poor, good
excellent
QUALITATIVE OR QUANTITATIVE?

Number of patients coming to a clinic per day.

Smoker or not (1.Yes 2.No)
Daily temperature
Pain score on a scale of 0 to 10
Medical record number
Classification of children in a day care centre (infant,
toddler, pre school)

27
QUALITATIVE OR QUANTITATIVE?
Have you heard of night blindness? (1. Yes 2.No)
What are causes of night blindness? (1. dietary
deficiency; 2. due to some disease; 3. due to bad
evils)
When did u start your professional carrier?
Did you have fever during past two weeks?(1.Yes
2.No)
If yes then how much fever? (in centigrade):
____________
Literacy status ( 1. Literate 2. Illiterate )
National identity card number

28
SCALES OF MEASUREMENT

29
SCALES IN QUALITATIVE DATA
Nominal scale data

Nominal being from Latin word the “name”

 Categories can be made
 Categories cannot be ranked/orderable
 Categories must be exclusive (categories must be made in such a
way that a datum will fit into one of the category)
 Categories must be exhaustive (all of the data must be fit into
established categories)
 Characterized by data that consist of names, labels, or
categories only. The data cannot be arranged in an ordering
scheme (such as low to high or high to low)

Example: survey responses yes, no, undecided, person may

30
be classified as male or female
SCALES IN QUALITATIVE DATA
Ordinal scale data
 Categories can be ranked or meaningfully ordered.
 Categories must be exclusive (categories must be made
in such a way that a datum will fit into one of the category)
 Categories must be exhaustive (all of the data must be fit
into established categories)

 involves data that may be arranged in some order, but

differences between data values or interval between
data values either cannot be determined or are
meaningless
Example: Course grades A, B, C, D, or E,

Levels of pain: severe , moderate, mild, no pain 31

SCALES IN QUANTITATIVE DATA
Interval scale data :
 Having equal numerical distance between data values or
equal intervals between data values
 like the ordinal level, with the additional property that the
difference between any two data values is meaningful.
 Magnitude of the any attribute can be precisely measured
but absolute amount of attribute can not be measured
because interval scale lacks a absolute zero point.
 There is no natural zero starting point. A temperature of
zero does not indicate absence of temperature. The data
can be added or subtracted meaningfully but not multiplied
or divided.

32
Example: two common temperature scales Celsius
(C) and Fahrenheit (F). We can see that same
difference exists between 10 c(50F) and 20c (68F)
and 25C (77F) and 35C (95F).But we can not say
that temperature of 20C is twice hot as a
temperature of 10C, because absolute zero is
arbitrary.

33
Ratio scaled Data
 include the natural zero starting point (where zero
indicates that none of the quantity is present).
 Zero is the absence of the characteristic being measured.
 All characteristics like interval scale of measurement.
 Can add / subtract / multiply / divide.

Example: Prices of college textbooks, height, weight

34
IDENTIFY THE SCALE OF
MEASUREMENT
Nominal or Ordinal Interval or ratio
Severity of pain (mild moderate, Height (in cm)
or sever) Weight (in Kg)
Level of education (illiterate, Age (in year)
can read or write, primary, Year of Schooling
secondary, metric, intermediate,
graduate post graduate) Duration of disease
Major causes of deaths in I Q of a person
developed countries Number of children
Sex (Male, Female) Grade points(0,1,2,3,4)
Medical Record number GPA (2.0,3.2)
Grades (A,B,C or D)
Nationality (Pakistani,
Afghani etc) 35
Passport Number
NOMINAL, ORDINAL, INTERVAL OR
RATIO SCALED?
Number of patients coming to a clinic per day.
Smoker or not (1.Yes 2.No)
Daily temperature
Pain score on a scale of 0 to 10
Medical record number
Classification of children in a day care centre (infant, toddler, pre
school)
Have you heard of night blindness? (1. Yes 2.No)
What are causes of night blindness? (1. dietary deficiency; 2. due to
some disease; 3. due to bad evils)
When did u start your professional carrier?
Did you have fever during past two weeks?(1.Yes 2.No)
If yes then how much fever? (in centigrade):____________
Literacy status ( 1. Literate 2. Illiterate )
National identity card number 36
 TH
ANKS

37