MITWPU

Fundamentals Stats

Shamim Mohammad, M.Phil., PhD.

 What is Statistics?

Croxton and Cowden according to

whom statistics may be defined as
the science, which deals with
collection, presentation, analysis and
interpretation of numerical data

2
What is bio or health Statistics?
• Biostatistics may be defined as application of
statistical methods to medical, biological,
psycho and public health related problems.
• It is the scientific treatment given to the medical
data derived from group of individuals or patients
 Collection of data.
 Presentation of the collected data.
 Analysis and interpretation of the results.
 Making decisions on the basis of such analysis
3
 Role of Statistics
Statistics finds an extensive use in PH and CM.
Statistical methods are foundations for public
health administrators to understand what is
happening to the population under their care at
community level as well as individual level.
Reliable information helps;
1. Assess community needs
2. Understand socioeconomic & psycho
determinants of health
3. Plan experiment in health research and analyze
results
4. Study diagnosis and prognosis of the disease for
taking effective action
5. Scientifically test the efficacy of new medicines
and 4
 Sources of
data

Records Surveys Experiments

Comprehensive Sample

5
 Organizing Data
Line List or Line Listing
•Whether one is conducting routine
surveillance, investigating an outbreak, or
conducting a study…compile information in a
organized manner.
•Organized like a spreadsheet with rows and
columns
•Each row is called record or observation
•Each column is called a variable and contain
information about gender, race, or DOB, etc.
6
7
 Variable
• A variable can be any characteristic
that differs from a person to person
such as height, sex, Dengue +/-, fever
present/absent.
• Most research begins with a general
question about the relationship between
two variables for a specific group of
individuals.
• Software: Epi Info available for free
download in CDC website 8
 Types of Variables
• Look at columns and rows
• Some values are numeric and some are descriptive.
• Variables can be classified into four types
1. Nominal-scale variable
2. Ordinal-scale variable
3. Interval-scale variable
4. Ratio-scale variable
Nominal & Ordinal…………Qualitative or Categorical or
discrete
Interval & Ratio Scale……….Quantitative or Continuous

9
Nominal Scale Variable
•Values are categories without any numerical
ranking such as;
(alive or dead, ill or well, vaccinated or
unvaccinated,…..etc.)
•Two mutually exclusive categories
•Also called dichotomous variable
Ordinal Scale Variable
Values can be ranked but not evenly spaced
Such as cancer stages, SES
Customer Satisfaction surveys
10
11
Likert Type Scale-Variant of OS
Interval difference between ordinal
variables cannot be concluded. Effectively
used in surveys, polls, and questionnaires .
•SEC such as rich, middle class, poor etc.
•Frequency of occurrence- very often,
often, Not often, Not at all
•Evaluating the degree of agreement-
TA, Agree, Neutral, Disagree, TD
•Understanding preferences-HP, Apple,
Lenovo, Dell, Acer
12
 Interval Scale variables
• Measured on equally spaced units, but
without a true 0 like
• zero arbitrary (Not True zero)
• Interval scales are sometimes useful in
statistics because they let you assign
numerical values to arbitrary
measurements, like an opinion
• Quantitative
• Third level of measurement

13
14
 Ratio Scale Variable
• Interval variable with true zero such as
height, weight, illness duration, etc.
• Ratio scale ranks the highest in the
four “levels of measurement”
• The ratio scale has all the qualities of
nominal, ordinal, and nominal scales
• Ratio scale has a true zero, that is,
the zero possesses a meaningful value.
• The common example of a ratio scale is
length, duration, mass, etc.
• All statistical analysis (descriptive &
inferential) possible 15
Summary

16
Level Description Attribute Statistical
methods used
1. Nominal Classification into mutually Sex; Religion Mode, Chi-square
exclusive categories based on Dead/alive
presence or absence of a
property

2. Ordinal Ordered based on level of Education, Median, ANOVA,

specific property satisfaction, Rank order
happiness correlation, Mann-
Whitney U test ,
Kruskal–Wallis H test

3. Interval Difference between objects or Temperature, T test, One way

people on a specific property ANOVA
based on intervals
e.g. Likert scale, Sematic
Differential scale

4. Ratio Objects or events with Height, All statistical

quantifiable level of property weight methods 17
ethods of presentation of da

Numerical presentation
Graphical presentation
Mathematical presentation
 Numerical Presentation
Tabular presentation (simple – complex)
Simple Frequency Distribution Table (S.F.D.T.)
Title
Name of variable
Frequency %
(Units of variable)
-
- Categories
-

Total
19
Distribution of 50 patients at the surgical department of
AAAAA hospital in May 2008 according to their ABO
blood groups

Blood Frequency %
group
A 12 24
B 18 36
AB 5 10
O 15 30
Total 50 100

20
 Complex Frequency Distribution Table
Distribution of 20 lung cancer patients at the chest
department of AAAAA hospital and 40 controls in
May 2008 according to smoking

Lung cancer
Total
Smokin Cases Control
g No. % No. % No. %

Smoke 38.3
15 75% 8 20% 23
r 3
Non 61.6
5 25% 32 80% 37
smoker 7
21
Total 20 100 40 100 60 100
 Graphical Presentation
• Line Graph
• Frequency Polygon
• Frequency Curve
• Histogram
• Scatter Plot
• Pie Chart
• Statistical Map

22
 Characteristics-Line Graph
• Line graphs are suitable for displaying
numerical (quantitative) data.
• The slope of the line indicates the rate of
change (the relative change) of y over time.
• A horizontal straight line indicates no
change.
• An upward or downward straight line slope
indicates a constant rate of increase or
decrease
• Two parallel lines indicate similar rate of
change over time.
23
 Line Graph

MMR/1000 Year MMR

60 1960 50
50
40 1970 45
30
20 1980 26
10
0 1990 15
Year
1960 1970 1980 1990 2000
2000 12

Maternal mortality rate of (country),

1960-2000
24
 Frequency Polygon

• Shows a frequency distribution

emphasizing the overall pattern in the
data
• Frequency polygons represent
a simple way to show data of
several histograms on the same
graphic

25
 Frequency Polygon
Age Sex Mid-point of
(years) interval
Males Female
s
20 - 3 (12%) 2 (10%) (20+30) / 2 = 25
30 - 9 (36%) 6 (30%) (30+40) / 2 = 35
40- 7 (8%) 5 (25%) (40+50) / 2 = 45
50 - 4 (16%) 3 (15%) (50+60) / 2 = 55
60 - 70 2 (8%) 4 (20%) (60+70) / 2 = 65
Total 25(100 20(100
%) %)
26
 Frequency Polygon
Males Females
%
40
35
Sex
30 M-
Age
M F P
25
20 (12% (10%
20- 25
) )
15
(36% (30%
10 30- 35
) )
5 (25%
40- 45
0 (8%) )
Age
25 35 45 55 65 (16% (15%
50- 55
) )
60- (20%
70
(8%) 65
)
Distribution of 45 patients at (place) , in (time)
by age and sex 27
 Frequency Curve
9
Female
Merits: Shows
8
7 Male skewness to the
6 distribution +/-
5
Kurtosis
Frequency

4
3
2
1
0
20- 30- 40- 50- 60-69
Age in years

28
 Characteristics of Histogram
• Shows the frequency distribution of
numerical data, either continuous
(such as height) or discrete (such as
mortality).
• Histograms can help visualise gaps in
the data, outliners or other unusual
observations.
• In intervention epidemiology histograms
are frequently used to present
occurrence (distribution) of onsets
of illness according to time.
Histogram

30
 Characteristics-Bar Graph

• Simple Bar Graph

• Grouped Bar Graphs
• Stacked Bar Graphs
• Component Bar Graphs

31
 Simple Bar Graph
%
45
40
35
30
25
20
15
10
5
0
Single Married Divorced Widowed
Marital Status
Marital status
32
 Grouped Bar Graphs
%
50
Male
40 Female

30
20
10
0
Single Married Divorced Widowed
Marital status
Marital Status

33
33
 Stacked Bar Graphs
•.

34
Component Bar Graph

35
 Characteristics-Pie Chart
• Circle provides a visual concept of the
whole (100%) and they are simple to use.
• they are best used for displaying statistical
information when there are no more than six
components
• Not useful when the values of each
component are similar because it is
difficult to see the differences between
slice sizes
• Can be very misleading if one presents
percentages based on a limited
36
number of cases
 Pie Chart
Number of Deaths by Cause Among 25–
34 Year Olds — United States, 2003

37
Doughnut chart

3838
 Reference

•Introduction to Epidemiology

39