EPIDEMIOLOGY
Presented by- Dr. Parikshit S Kadam
( JR-1)
Content
• Introduction
• Definition
• History
• Aims of epidemiology
• Tools of measurements
• Epidemiological studies
• Bias
• Association and causation
• Conclusion
• References
Introduction
• Epidemiology is the basic science of Preventive and
Social Medicine
• Epidemiology is scientific discipline of public health
to study diseases in the community to acquire
knowledge for health care of the society
• Epi – upon
demos- people
logos – study or science
Definition
• “ The branch of medical science which deals with
treatment of epidemics”
Parkin ( 1873)
• “ The study of the distribution and determinants of
disease frequency in man”
MacMohan ( 1960)
• “The study of the distribution and determinants of
health-related states or events in specified populations,
and the application of this study to the prevention and
control of health problems”
John M. Last (1988)
History
• First known epidemiologist was Hippocrates ( 460-375
B.C)
• “ No disease”, he said, “is sent by evils or demons, but
is the result of natural causes”
• Claudius Galen (130-200 A.D) a Greek wrote that “
reason alone discovers some things; experience alone
discovers some things; but to find others, requires both
reason and experience”
• In the 17th century, Thomas Sydenham (1624-1689) a
London physician, stressed the importance of careful
observations
• He wrote the history of disease and was called the “
Father of English medicine, or the English
Hippocrates”
• John Snow (1813-1858) is considered as the “ Father
of Epidemiology”
• Develop interest in the epidemic of cholera in London,
in August 1854
• Similar study was done by William Budd (1811-1880)
on typhoid fever
• First dental field study was reported in Britain 1803 by
Sir John Lincour
• Collected details of the health habits and dental state
of 96 old men all aged over 80 years
• Edwin Saunders, a young dentist studies the eruption
of teeth between ages 9 and 13
• In 1837 addressed his findings to parliament in a
report entitled, “ The teeth a test of age”
Aims Epidemiology
• To describe the size and distribution of disease
problems in human populations
• To identify etiological factors (risk factors) in the
pathogenesis of disease
• To provide data essential to the planning,
implementation and evaluation of health services for
the prevention, control and treatment of disease and
for setting priorities among those services
Principles Of Epidemiology
1. Exact observation
2. Correct interpretation
3. Rationale explanation
4. Scientific construction
Tools In Epidemilogy
• Numerator – Number of events in a population during
specified time
• Denominator
1. Total population
- Mid-year population
- Population at risk
2. Total events
10
100
• Basic tools are
1. Rate
2. Ratio
3. Proportion
• Comparison between 2 same things
• Numerator is the part of denominator
RATE
• Comparison between 2 different things
• Numerator is not part of denominator
RATIO
• Numerator is the part of denominator
PROPORTION
Rate
• It is the frequency of a disease or characteristics
expressed per unit size of the population or group in
which it is observed
• Rate = ×10n
Number of events in a specific period
Population at risk of experiencing the
events or disease
• 2000 × 1000
1. Crude rate
2. Specific rate
3. Standardized rate
5000
Ratio
• “It expresses a relation in size between two random
quantities, in this numerator is not a component of the
denominator”
• x : y or x
y
Proportion
• A proportion is a ratio which expresses the relation in
magnitude of a part of the whole
• Numerator always a part of denominator
Measurements in Epidemiology
• Measurement of MORTALITY
• Measurement of MOBIDITY
• Measurement of DISABILITY
• Measurement of NATALITY
• Measurement of presence, absence or distribution of
the characteristics or attributes of the disease
• Measurements of medical needs, health care facilities,
utilization of health care services and other health
related events
• Measurement of presence, absence or distribution of
the environment and other factors suspected of causing
the disease
• Measurement of demographic variables
Measurement of MORTALITY
• Mortality is an integral part of demography
• Many countries have routine systems for collecting
mortality data. Traditionally and universally, most
epidemiological studies begin with mortality data
Problems
The
incomplete
reporting of
deaths
Lack of
accuracy
Lack of
uniformity
Choosing a
single cause
of death
Uses
• In indicating priorities for health action
• Allocation of resources, In designing intervention
programmes, And in the assessment and monitoring of
public health programmes
Mortality rates
1. Crude death rate :- “ the number of deaths per 1000
people in a population in a given year ”
Crude death rate =
No. of death during the year in a population
Mid-year population
2 . Specific death rate:- A specific death rates measures
the number of deaths among people in a category per
1000 people in that category in a given year
Specific death rate = No. of deaths due to cause
Mid-year population
3. Age-specific death rate:- Death rate specific to a given
age group
4. Case fatality rate :- Represents the killing power of a
disease
5. Proportional mortality rate :- The number of deaths
due to a particular cause in a specific age groups per
100 or 1000 total deaths
6. Standardized rates:- The overall rates adjusted for the
affects of differences in population composition
Factors affecting mortality rate
• Birth rate
• Density of population
• Geographical
• Season
• Epidemic experience
• Secular variation
MEASUREMENT OF MORBIDITY
‘ Morbidity’ as “any departure, subjective or objective,
from a state of physiological well being ’’.
Linenfeid A M.,Linenfeid D E. Foundation of epidemiology 1990
Uses
Describe the
extent and
nature of the
disease
Provide more
comprehensive
and more
accurate and
clinically
relevant
information
Serve as
starting point
for etiological
studies
Needed for
monitoring
and evaluation
of disease
control
activities
Incidence
• The number of new cases occurring in a defined
population during a specified period of time
• It refers to
1. Only to new cases
2. During a given period
3. In a specified population or population at risk
• Incidence rate = ×1000
Number of new cases of a specific disease
during given time period
The population at risk
Episode
Cumulative
• when the population is
exposed to risk for a
limited period of time
such as in epidemic
Attack
rate
• The number of exposed
persons developing the
disease within the range
of incubation period,
following exposure to
the primary case
Secondary
attack
rate
Uses
Gives clues to
research into the
etiology and
pathogenesis of
disease
Study of
distribution of
disease
Helps in taking
action to
control disease
Useful in
evaluating the
efficacy of
preventive and
therapeutic
measures
Prevalence
• The total number of all current cases (old+new)
existing at a given point in time, or over a period of
time in given population
Point
prevalence
Period
prevalence
• Uses of prevalence rate is
 Useful in estimating the magnitude of disease or
health problems of community
 Helpful in identifying the potential high – risk
population
 Useful in administrative and planning purposes like
assessing manpower needs in health services, delivery
of health services etc.
Longer duration of the disease
Prolongation of life of patient
Increase in new cases
In-migration cases
Out-migration of healthy patients
Improved diagnostic facilities
Shorter duration of the disease
High case-fatality rate from disease
Decrease in new cases
In-migration of healthy people
Out-migration of cases
Improved cure rate of cases
Incidence Prevalence
Numerator Number of new cases of disease
during specific period of time
Number of existing cases of
disease at a given point of time
Denominator Population at risk Population at risk
Focus Whether the event is a new case
Time of onset of the disease
Presence or absence of a disease
Time period is arbitrary
Uses Express the risk of becoming ill
To study acute disease
Useful for studies of causation
Estimate the probability of a
population being ill at the
period of time being studied
Useful for study of chronic
disease and implication of
health services
RELATION BETWEEN
PREVALENCE & INCIDENCE
• Prevalence depends upon two factors, the incidence &
duration of illness
• Prevalence = Incidence × Mean duration
P = I × D
Epidemiological
study
Observational
Group
Descriptive or
analytical
Ecological
study
Individual
Descriptive Analytical
Experimental
Individual
Randomised
control trial
Group
Field trial
Cross-sectional Cohort study Case control
DESCRIPTIVE EPIDEMIOLOGY
• A simple description of the health status of a
community
• Based on routinely available data or data obtained in
special surveys
• Is often the first step in an epidemiological
investigation
Formulating an etiological hypothesis
Comparing with known indices
Measurement of the disease
Describing the disease in terms of
Time Place Person
Defining the disease under study
Defining the population to be studies
1. Defining population to be studied
• It is a ‘Population study’ not of an individual
• Defining population by total number and composition
(age, sex, occupation etc. )
• Defined population- can ‘whole population’or ‘a
representative sample’
• It provides ‘denominator’ for calculating rates and
frequency
2. Defining disease under study
• Operation Definition - of disease is essential for
measuring the disease in defined population
• ‘Case definition’ should be adhered throughout the
study
3. Describing disease
Time Year, Month, Week, Season, Duration
Place Country, Region, Climatic zone, Urban/rural,
Community, Cities, Towns
Person Age, Sex, Marital status, Occupation,
Education, Socioeconomic status
Time
distribution
Short-term
Common
source
Single
exposure or
point source
Continuous or
multiple
exposure
Propagated
epidemics
Person to
person
Arthropod
vectors
Animal
reservoir
Periodic
Seasonal Cyclic trends
Long-term
Place distribution
• Variation in frequency of different disease manifestation from
place to place has long been organized
• The distribution of disease according to places can be classified
as
• International variation
• National variation
• Rural – Urban variation
• Local variation/ distributions
INTERNATIONAL VARIATION
• Examine mortality and morbidity in relation to socioeconomic
factors, dietary differences and difference in culture and
behaviour
• Ex : Oral cancer has highest incidence in countries like India
, Bangladesh, Srilanka & Pakistan .
• Breast cancer shows highest prevalence in the countries of the
western world like Netherlands , England and Wales
• Britain has highest rates for lung cancer
NATIONAL VARIATION
• Variation in disease occurs in the same country
• Ex : In India endemic goiter, malaria, fluorosis, leprosy with
some parts of country more affected & other parts less
affected or not affected at all
RURAL – URBAN VARIATION
• It is a well established fact that health and disease are not
equally distributed in urban and rural population
• Chronic bronchitis, lung cancer, CVS disease - common in
urban areas
• Skin and zoonotic infections - in rural areas
LOCAL DISTRIBUTER
• The preparations of maps showing the distribution of cases
of a disease within the local community is a long
established epidemiologic procedures
• ‘Spot maps’ or ‘shaded maps’ are used to study the
variations in disease frequency
• Eg. If map show clustering of cases it may suggest common
source of infection
Migration study
• It is of two types;
• Comparing the rate of occurrence of disease and the death rate
for migrants with those if their same group who have stayed at
home
• Comparing the migrants with the local population of the host
country provides valuable information on the genetically
different groups living in a similar environment
• Anderson M. An introduction to epidemiology. 2nd edition
• PERSON DISTRIBUTION
• In descriptive studies, disease is further characterized by
defining the person who developed disease
1. Age :
• It is variable and must always be considered in epidemiologic
study
• Certain disease are more prevalent in specific age group
• Measles – children
• Cancer – middle age
• Atherosclerosis – old age
2 . SEX
• Chronic conditions are more common in females like
thyrotoxicosis, diabetes mellitus, obesity, arthritis etc
• In Males, diseases include peptic ulcer, respiratory
cancer, lung cancer etc
3. Ethnic groups / Ethnicity
• Can be identified in terms of race , religion , place of birth or
combination of three
• Examples :Dental caries-western countries, Periodontal
disease - in Blacks
4. Occupation
- Alter the habit pattern of employee like sleep, alcohol,
smoking
- for identification of risk associated with exposure to
chemicals, physical , biologic agents peculiar to certain
occupations
5. Socioeconomic status
• It has different meanings for different persons , income ,
living conditions, occupation, education and social prestige
• The individuals belonging to the upper social classes exhibit
a longer life expectancy and better health and nutritional
state than the individuals belonging to lower social classes
6. Marital status
• Marital is a descriptive variable that appears on
medical, dental and civil records almost as
regularly as age and sex
• The married persons have lower mortality rates
from nearly all causes of death , than the single
,widowed or divorced person
4. Measurement of disease
• To obtain the clear picture of ‘disease load’ in the
population
• In terms of Mortality, Morbidity and Disability
• Morbidity has two aspects –
- Incidence – Longitudinal Studies
- Prevalence - Cross-sectional studies
5. Comparing with known indices
• Basic epidemiological approach –
1. making comparisons
2. Asking questions
• Making comparison with known indices in population
• By making comparisons - clues about
- Disease etiology
- High risk population
6. Formulation of etiological hypothesis
• A hypothesis is supposition arrived at observation or
reflection
• Hypothesis should specify –
1. Population
2. Specific cause – risk factors/exposures
3. Outcome – disease/disability
4. Dose-response relationship
5. Time response relationship
Smoking 40-50 beedis per day, will result in leukoplakia among 4% of beedi smokers
after 10 years
Uses of Descriptive Epidemiology
1. Provide data of magnitude of problem- disease load
2. Provide clues for etiology
3. Provide background data for planning, organizing and
evaluating the preventive and curative services
4. Contributes to research
Analytical Studies
• Analyzing relationships between health status and
other variables
• The objective is testing the hypothesis
• Subject of interest is individual, but inference applied
to population
• TYPES
1. Case-control studies(Case reference studies)
2. Cohort studies (Follow-up studies)
Case-control studies
• It is first approach to testing causal hypothesis,
• Especially for rare disease
• Three features:-
1. Both exposure and outcome (disease) has occurred
2. Study proceeds backwards from effect to cause
3. It uses a control group to support or refuse a inference
Population
Cases
Control
Exposed
Non-exposed
Exposed
Non-exposed
Time
Direction of inquiry
• Basic steps in Case-control study:-
1. Selection of cases and controls
2. Matching
3. Measurement of exposure
4. Analysis and interpretation
1. Selection of cases and controls
• CASES –
- Case definition – (Diagnostic criteria and Eligibility criteria)
- Source of Cases – (Hospital or General population)
• CONTROLS
- Free from the disease under study
- Similar to the cases in all other aspects
• Sources:-
Hospital, Relative, Neighbourhood, General population
2. Matching
• Matching is process by we selecting controls in a manner
that they are similar to cases in all variables
• Matching is essential for comparability and for
elimination of confounding bias
• A Confounding factor is a factor which associated with
both exposure and disease and unequally distributed in
study and control groups
• Matching procedure –
- Group matching (Strata matching)
- Pair matching
3. Measurement of exposure
• Information of exposure of risk factor should be obtain in
same manner for both cases and controls
• Information obtain by:-
- Questionnaire
- Interviews
- Hospital records
- Employment records
4. Analysis and interpretation
1. Exposure rates:- Estimation of rates of exposure of
suspected factor among cases & controls
2. Odds Ratio:- Estimation of disease risk associated
with exposure among cases & controls
1. Exposure rates
CASES (Lung
Cancer)
CONTROLS
(Without
Lung Cancer)
TOTAL
SMOKERS 33 (a) 55 (b) 88 (a+b)
NON-
SMOKERS
2 (c) 27 (d) 29 (c+d)
TOTAL 35 (a+c) 82 (b+d) N= a+b+c+d
2. Odds Ratio
• It is estimation of risk of disease associated with exposure
• It measures strength of association of risk factor and
outcome(disease)
• Odds Ratio = 33 x 27 / 55 x 2 = 8.1
• Smokers have risk of developing lung cancer 8.1 times
higher than non-smoker
ODDS RATIO = AD/BC
Cohort Studies
• Also known as prospective study, longitudinal study,
incidence study, forward looking study
• Cohort is group of people with similar characteristics
• Begin with a group of people who are free of disease.
• Whole cohort is followed up to see the effect of
exposure
Population
Non-exposed
Exposed
Time
Direction of inquiry
People
without the
disease
Disease
No disease
Disease
No disease
• Types of Cohort Studies:-
1. Prospective cohort studies
2. Retrospective cohort studies
3. Combination of retrospective and prospective cohort
studies
Elements of Cohort studies
1. Selection of study subjects
2. Obtaining data on exposure
3. Selection of comparison group
4. Follow-up
5. Analysis
1. Selection of study subjects
• General population or
• Special group (Doctors, Teachers, Lawyers)
• Cohort should be selected from the group with
special exposure under study
2. Obtaining data on exposure
a. Cohort members- questionnaire, interview
b. Review of records
c. Medical Examination or tests
d. Environmental surveys
• Categorized according to exposure –
1. Whether exposed or not exposed to special causal
factor
2. Degree of exposure
3. Selection of comparison group
• Subjects are categorized in group
according to degree of exposure &
mortality and morbidity compared
Internal comparison
• When degree of exposure not known
• Control group with similar in other
variable
External
comparison
• Comparison with the general population as
exposed group
Comparison with
general population
4. Follow-up
• Regular follow-up of all participants
• Measurement of variable depends upon outcome
• Procedure:-
1. Periodical medical examination
2. Review of hospital records
3. Routine surveillance and death records
4. Mailed questionnaire and phone calls
5. Analysis
• Data are analyzed in terms of :–
a. Incidence rates-
Among exposed and non-exposed
b. Estimation of risk.:-
1. Relative Risk
2. Attributable Risk
Incidence rates
SMOKING DEVELOP
ED LUNG
CANCER
NOT
DEVELOP
ED LUNG
CANCER
TOTAL
YES 70 (a) 6930(b) 7000 (a+b)
NO 3(c) 2997 (d) 3000 (c+d)
Relative Risk
• Relative risk is the ratio of the incidence of disease
among exposed and incidence among non-exposed
• It is direct measure of strength of the association
between suspected cause and effect
Attributable Risk
• AR is the difference in incidence rates of disease among
exposed and non-exposed group
• AR= I.R. among exposed - I.R. among non-exposed
I Incidence among exposed x100
• AR is the proportion of disease due to particular risk factor
exposure
• That means- amount of disease eliminated if the suspected
risk factor is removed
Population Attributable Risk
• Population A. R. = I.R. in total population – I.R. among non-
exposed
I.R. in total population X 100
• Population Attributable Risk is useful concept as it give the
magnitude of disease that can be reduced from the
population if the suspected risk factor is eliminated or
modified
Exposure and outcome
Exposure Outcome Remarks Direction
Prospective
cohort study
Occurred Followed-
up
Start with
exposure
Forward
looking
Retrospective
cohort study
Occurred Occurred Start with
exposure
Forward
looking
Mixed cohort
study
Occurred Occurred Start with
exposure
Forward
looking
Case control
study
Occurred Occurred Start with
outcome
Backward
looking
Cross-sectional
study
Occurred Occurred Both exposure
and outcome
assesed
Neither forward
nor backward
looking
Case control Cohort
Starts with the disease, proceeds from
effect to cause
Starts with the people exposed to the risk
factor, proceeds from cause to effect
It is first approach to test a hypothesis Reserved for testing precisely formulated
hypothesis
Involves fewer subjects Involves large number of subjects
Yields results quickly Results are delayed due to long follow up
periods
Suitable for studying rare diseases unsuitable
Gives relative risk Gives relative risk and attributed risk
Inexpensive Expensive
Characteristics Cross-sectional Case-control Cohort study
Time One time point Retrospective Prospective
Other names Prevalence study Case reference study Longitudinal study
Forward looking study
Follow up study
Incidence study
Incidence No No Allows
Prevalence Allows No No
Casuality No Yes Yes
Role of disease Measures disease Begin with disease End with disease
Assesses Association of risk factors and
disease
Many risk factors for single
disease
Single risk factor affecting
many diseases
Data anlaysis Chi-square to assess
association
Odds ratio to estimate risk Provide direct estimate of
relative risk
Advantages Used to calculate prevalence
Faster
Quick and inexpensive
Useful to study rare diseases
Require few subjects
Easy to conduct
Incidence can be calculated
Provides direct estimate of
relative risk
Disadvantages Unusable for acute diseases Recall bias and selection bias
are present
Miss the undiagnosed or
asymptomatic cases
Expensive
Time consuming
Involves large number of
subjects
EXPERIMENTAL EPIDEMIOLOGY
• Interventional or experimental study involves attempting to
change a variable in subjects under study
• The effects of an intervention are measured by comparing
the outcome in the experimental group with that in a
control group
Objectives of Experimental Studies
1. To provide ‘scientific proof’ for etiology of disease and
risk factor which may allow modification of occurrence of
disease
2. To provide a method of measurement for effectiveness and
efficiency of therapeutic / preventive measure for disease
3. To provide method to measurement for the efficiency
health services for prevention, control and treatment of
disease
Types of Experimental Studies
1. Randomized Control Trials
2. Field Trials & Community Trials
Randomized Control Trials
• RCT is a planned experiment designed to asses the efficacy
of an intervention in human beings by comparing the effect
of intervention in a study group to a control group
• The allocation of subjects to study or control is determined
purely by chance (randomization)
• For new programme or new therapy RCT is best method of
evaluation
Basic Steps in RCT
1. Drawing-up a protocol
2. Selecting reference and experimental population
3. Randomization
4. Manipulation or Intervention
5. Follow-up
6. Assessment of outcome
The Protocol
• Study conducted under strict protocol
• Protocol specifies :- aim, objectives, criteria for selection of
study and control group, sample size, intervention applied,
standardization and schedule and responsibilities
Reference and Experimental
population
• Reference population (Target Population)
• Is the population in which the results of the study is
applicable
• A reference population may be – Human being, country,
specific age, sex, occupation etc.
• Experimental Population (Study Population)
• It is derived from the target population
• Three criteria:-
1. They must be representative of RP
2. Qualified for the study
3. Ready to give informed consents
Randomization
• It is statistical procedure to allocate participants in groups –
Study group and Control group
• Randomization gives equal chance to participants to be
allocated in Study or Control group
• Randomization is an attempt to eliminate ‘bias’ and allow
‘comparability’
• Randomization eliminates ‘Selection Bias’
• Matching is for only those variable which are known
• Randomization is best done by the table of random numbers
• In Analytical study there is no randomization, we already
study the difference of risk factor. So only option is Matching
Manipulation or Intervention
• Manipulation by application of therapy or reduction or
withdrawal of suspected causal factor in Study and
control group
• This manipulation creates independent variable whose
effect is measured in final outcome
Follow-up
• Follow-up of both study and control group in standard
manner in definite time period
• Duration of trial depends on the changes expected in
duration since study started
• Some loss of subjects due to migration, death is k/as
Attrition
Assessment
• Final step is assessment of outcome in terms of
positive and negative results
• The incidence of positive and negative results are
compared in both group- Study group and Control
group
• Results are tested for statistical significance (p value)
Study designs
• Concurrent parallel study design
• Cross-over type of study design
Field trials
• Field trials, in contrast to clinical trials, involve people who
are healthy but presumed to be at risk
• Data collection takes place “in the field,” usually among
non-institutionalized people in the general population
• Since the subjects are disease-free and the purpose is to
prevent diseases
Community Trials
• In this form of experiment, the treatment groups are
communities rather than individuals
• This is particularly appropriate for diseases that are
influenced by social conditions, and for which
prevention efforts target group behaviour
Clinical trials
• Phase I – Human pharmacology and safety
• Phase II – Therapeutic exploration and dose ranging
• Phase III – Therapeutic conformation
• Phase IV – Post marketing surveillance
Potential errors in epidemiological
studies
• Bias may arise from the errors of assessment of
outcome due to human element
• Apprehension
• Attention (Hawthorne effect)
• Berksonian bias
• Recall bias
• Neyman bias
Bias in cohort studies Selection bias
Information bias
Confounding bias
Post hoc bias
Bias in control studies Berkesonian bias
Recall bias
Telescoic bias
Interviewer’s bias
Bias due to confounding
Prevalence incidence bias
Bias in RCT Subject variation
Observer bias
Investigator bias
Others Hawthorne bias
Pygmalion effect
Blinding
• Single blinding
• Double blinding
• Triple blinding
Association and causation
1. Causal association
• Direct causal association
• Indirect causal association
2. Non-causal association
Conclusion
• Epidemiological research can be particularly useful in
promoting public health because it provides evidence
to enable the public health practitioners to identify
priorities and explore the risk factors
References
• Soben Peter - Essentials Of Preventive And
Community Dentirsty-sixth Edition
• Park - A Textbook Of Prventive And Social
Medicine - Nineteenth Edition
• Review of preventive and social medicine by vivek
jain
THANK YOU
BIOSTATISTICS
Presented by- Dr. Parikshit Kadam
( JR-1)
CONTENTS
• Introduction
• Categories of research
• Scientific methods
• Definition
• Uses of biostatistics
• Common statistical terms
• Sources and collection of Data
• Presentation of Data
• Analysis and interpretation
• Statistical averages
• Measures of Dispersion
• Sampling and sampling methods
• Sampling errors
• Tests of significance
• Correlation and regression
• Conclusion
• References
• The word statistics comes from the italian word “statista”
meaning “statesman” or the german word “statistik” which
means a political state.
• John Graunt(1620-1674) – Father of health statistics
Statistics is the science of compiling,
classifying and tabulating numerical data
and expressing the results in a
mathematical or graph form
Biostatistics is that branch of statistics
concerned with mathematical facts and
data related to biological events
• We, medical and dental students during period of our
study, learn best methods of diagnosis and therapy
• After graduation, we go through research papers
presented at conferences and in current journals to
know new methods of therapy, improvement in
diagnosis and surgical techniques
• It must be admitted that essence of papers contributed
to medical journals is largely statistical
• Training in statistics has been recognized as
“indispensible” for students of medical science
• For eg. if we want to establish cause and effect
relationship, we need statistics
• If we want to measure state of health and also burden
of disease in community, we need statistics
• Statistics are widely used in epidemiology, clinical
trial of drug vaccine, program planning, community
medicine, health management, health information
system etc.
• The knowledge of medical statistics enables one to
develop a self- confidence & this will enable us to
become a good clinician, good medical research
worker, knowledgeable in statistical thinking
• Everything in medicine, be it research, diagnosis or
treatment depends on counting or measurement
• According to Lord Kelvin, when you can measure
what you are speaking about and express it in
numbers, you know something about it but when you
can not measure, when you can not express it in
numbers, your knowledge is of meagre and
unsatisfactory kind
• In Public Health or Community Health, it is called
Health Statistics
• In Medicine, it is called Medical Statistics. In this we
study the defect, injury, disease, efficacy of drug,
serum and line of treatment, etc.
• In population related study it is called Vital Statistics.
e.g. study of vital events like births, marriages and
deaths
127
Research
Basic
v/s
Applied
Observational
v/s
Experimental
Qualitative
v/s
Quantitative
Conceptual
v/s
Empirical
BASIC V/S APPLIED
• Basic research is usually considered to involve a
search for knowledge without a defined goal of
utility or specific purpose
• Applied research is problem-oriented, and is directed
towards the solution of an existing problem
OBSERVATIONAL V/S
EXPERIMENTAL
• Observational – to observe things
happening without interfering with it
• Experimental – manipulating some
aspect of environment and observing
its effects
QUALITATIVE V/S
QUANTITATIVE
• Qualitative research – deals with subjective
aspects
• Quantitative research – based on
measurement of quantity or amount
(objective aspects )
CONCEPTUAL V/S EMPIRICAL
• Conceptual – related to some abstract idea
or theory
• Empirical – experience or observation alone
are the tools of research (data based
research )
PPRIMARY & SECONDARY
RESEARCH
• PRIMARY RESEARCH- first hand
reports of facts or findings
• SECONDARY RESEARCH- from
primary research
132
SCIENTIFIC METHOD
Problem
formulation
Hypothesis
formulation
Data collection
Analysis and
interpretation
Writing a
report
DEFINITIONS
• American Heritage Dictionary defines statistics as:
"The mathematics of the collection, organization, and
interpretation of numerical data, especially the analysis
of population characteristics by inference from
sampling”
• The Merriam-Webster’s Collegiate Dictionary
definition is: "A branch of mathematics dealing with
the collection, analysis, interpretation, and presentation
of masses of numerical data"
• A Simple but Concise definition by Croxton and
Cowden: “Statistics is defined as the Collection,
Presentation, Analysis and Interpretation of numerical
data”
• “Statistics defined as the science of
 Collection
 Organisation
 Presentation
 Analysis and interpretation of numerical data”
Test difference is
real or chance
Study the correlation
Evaluate the efficacy
of vaccines, sera
Measure mortality
and morbidity
Evaluate
achievements of
public health
programs
Help promote health
legislation and create
administrative
standards for oral
health
Common statistical terms
• Variable:- A characteristic that takes on different
values in different persons, places/ things
• Constant:- Quantities that do not vary such as π =
3.141, e = 2.718. These do not require statistical study.
In Biostatistics, mean, standard deviation, standard
error, correlation coefficient and proportion of a
particular population are considered constant
• Observation:- An event and its measurement. for eg..
BP and its measurement
• Observational unit:- The “sources” that gives
observation for eg. Object, person etc. in medical
statistics:- terms like individuals, subjects etc are used
more often
• Data :- A set of values recorded on one or more
observational units
• Population:- It is an entire group of people or study
elements persons, things or measurements for which
we have an interest at particular time
• Sampling unit:- Each member of a population
• Sample:- It may be defined as a part of a population
• STATISTIC/ DATUM:- Measured/ counted fact or piece of
information such as height of person, birth weight of baby
• STATISTICS/ DATA:- Plural of the same such as height of
2 persons, birth weight of 5 babies, plaque score of 3 person
• BIOSTATISTICS:- Term used when tools of statistics are
applied to the data that is derived from biological sciences
such as medicine
• Demographic data comprises of population size, geographic
distribution, ethnic groups, socio economic factors and their
trends over time. Such data are obtained from census/
surveys, experiments, hospital records and other public
service reports and are important determinants for oral health
care programs
DATA
Qualitative
Data
Nominal Ordinal
Quantitative
Data
Discrete Continuous
COLLECTION
OF DATA
PRIMARY
SOURCE
SECONDARY
SOURCE
Questionnaire
method
Oral health
examination
Direct
personal
interviews
• Main sources for collection of medical statistics:
1. Experiments
2. Surveys
3. Records
• Experiments and surveys are applied to generate data
needed for specific purposes
• While Records provide ready- made data for routine
and continuous information
Methods of collection of data
• Method of direct observation:- Clinical signs and symptoms
and prognosis are collected by direct observation
• Method of house to house visit:- Vital statistics and morbidity
statistics are usually collected by visiting house to house
• Method of mailed questionnaire:- This method is followed in
community where literacy status of people is very high
Tabulation
Master table
Simple table
Frequency distribution
table
Chartsanddiagrams
Bar chart
Pie diagram
Line diagram
Histogram frequency
polygon
Cartogram
Pictogram
Scatter diagram
Tabulation
• As simple as possible
• Data must be according to size or importance,
chronologically or alphabetically
• Should be self-explanatory
• Each row and column labelled concisely and clearly
• Title should be clear, concise and to the point and it
should be separated from body of the table by lines or
spaces
Simple Table
States Population 1st march 2011
Andhra pradesh 8,46,65,533
Madhya pradesh 7,25,97,565
Uttar pradesh 19,95,81,477
Karnataka 7,14,83,435
Rajasthan 18,23,45,998
kerela 6,43,35,772
Frequency distribution table
• The following figures are the ages of patients admitted to a hospital
with poliomyelitis.. 8, 24, 18, 5, 6, 12, 14, 3, 23, 9, 18, 16, 1, 2, 3, 5, 11,
13, 15, 9, 11, 11, 7, 106, 9, 5, 16, 20, 4, 3, 3, 3, 10, 3, 2, 1, 6, 9, 3, 7, 14,
8, 1, 4, 6, 4, 15, 22, 2, 1, 4, 6, 4, 15, 22, 2, 1, 4, 7, 1, 12, 3, 23, 4, 19, 6,
2, 2, 4, 14, 2, 2, 21, 3, 2, 1, 7, 19
Age Number of patients
0-4 35
5-9 18
10-14 11
15-19 8
20-24 6
Attractive to eyes
Give a bird’s eye view of entire data
Lasting impression
Facilitate comparison of data
Title self
explanatory
Simple and
consistent
Values on x-axis
and frequency
on y-axis
Few lines drawn
in graphs
Scale of
presentation
mentioned
Scale of
division
proportional
Quantitative
data
• Histogram
• Frequency polygon
• Frequency curve
• Line chart or graph
• Cumulative frequency
diagram
• Scatter diagram
Qualitative
data
• Bar diagram
• Pie or sector diagram
• Pictogram
• Map diagram
Frequency polygon
Frequency curve
Line Diagram
10
25
60
85
0
10
20
30
40
50
60
70
80
90
0 1 2 3 4 5
Patients with
periodontitis
Biostatistics 157
Cumulative Frequency Diagram
25
35
40
45
55
70
90
0
10
20
30
40
50
60
70
80
90
100
0 to
10
yrs
10 to
20
yrs
20 to
30
yrs
30 to
40
yrs
40 to
50
yrs
50 to
60
yrs
60 to
70
yrs
Prevalence of Dental
Caries ( in percent)
Biostatistics 158
Scatter or Dot diagram
0
2
4
6
8
10
12
14
0 5 10 15
Carious lesion
Sugar Exposure
Bar chart
• Length of bars drawn vertical or horizontal is
proportional to frequency of variable
• Suitable scale is chosen
• Bars usually equally spaced
Biostatistics 160
Bar chart
• They are of three types
- Simple bar chart
- Multiple bar chart
• Two or more variables are grouped together
- Component bar chart
• Bars are divided into two parts
• Each part representing certain item and
proportional to magnitude of that item
Biostatistics 161
Simple bar chart
0
50
100
150
200
250
300
1st Qtr 2nd Qtr 3rd Qtr 4th Qtr
Number of CD
Patients
Biostatistics 162
Multiple bar chart
250
320
45
180
370
80
220
280
95
290
390
40
0
50
100
150
200
250
300
350
400
1st Qtr 2nd Qtr 3rd Qtr 4th Qtr
CD Patients
RPD Patients
FPD Patients
Biostatistics 163
Component bar chart
1500
1850
1400
2100
300
450
200
500
0
500
1000
1500
2000
2500
3000
1st Qtr 2nd Qtr 3rd Qtr 4th Qtr
Patients to prostho
Patients to other
Departments
Biostatistics 164
Pie chart
200, 31%
150, 24%
180, 29%
70, 11%
30, 5%
PROSTHO
CONSO
PERIO
ORTHO
PEDO
Probability
distribution(P)
Variables(V)
Population (U)
• Is collection of units of observation that are of interest
and is the target of investigation
• It is a state, condition, concept or event whose value is free
to vary within the population
• A variable is an attribute that describes a person, place or
thing
Qualitative (categorical) Quantitative (numerical)
Variables
Categorical
Nominal
Categories are
mutually
exclusive and
unordered
e.g –
gender,blood
group
Ordinal
Categories are
mutually
exclusive but
ordered
e.g- stage of
disease, pain
score(mild/mod
erate severe)
Numerical
Discrete
Integer, values
or counts
e.g – no. of
teeth with
caries
Continuous
Any value in a
range of values-
e.g weight in
kgs, height in
cms
Variables
Independent
variables
Dependent
variables
Confounding
or
intervening
variables
Background
variables
• P- value is defined as the probability under the assumption of
null hypothesis of obtaining a result equal to or more extreme
than that was actually observed
Binominal distribution
• Two parameters
• Occurs when a fixed number
of subjects
• Characteristic is dichotomous
in nature
• P or 1-p
Normal distribution
• Mathematical curve
represented by two quantities
m and s
Should be easy to understand and compute
Should be based on each and every item in
series
Should not be affected by extreme
observations
Sampling stability
PROPERTIES
MEAN
• Simplest
measure
MEDIAN
• Middle value
MODE
• Occurs with
greatest
frequency
Mode = 3 Median – 2 Mean
• For eg.. the income of 7 people per day in rupees are as
follows. 5, 5, 5, 7, 10, 20, 102= (total 154)
• Mean = 154/7 = 22
• Median= 7
• Median, therefore, is a better indicator of central tendency
when more of the lowest or the highest observations are
wide apart
• Mode is rarely used as series can have no modes, 1 mode
or multiple modes
Measures of Dispersion
• Widely known measures of dispersion are
a. The Range
b. The Mean or Average Deviation
c. The Standard Deviation
• Range : Simplest difference between highest and lowest
figures for eg.. Diastolic BP – 83, 75, 81, 79, 71, 90, 75, 95,
77, 94 so, the range is expressed as 71 to 95 or by actual
difference of 24
Mean deviation
• It is the summation of difference or deviations from the
mean in any distribution ignoring the + or – sign
• Denoted by MD
MD = € ( x – x )
n
X = observation
X = mean
n = no of observation
Standard deviation
• Also called root mean square deviation
• It is an improvement over mean deviation used most
commonly in statistical analysis
• Denoted by SD or s for sample and σ for a population
• Denoted by the formula
SD = € ( x – x )2
n or n-1
Coefficient of variation
• It is used to compare attributes having two different
units of measurement e.g. height and weight
• Denoted by CV
CV = SD X 100
Mean
and is expressed as percentage
Bell shaped
Perfectly symmetrical
Total area of curve is one,
mean is zero and standard
deviation one
All three measures of central
tendency coincide
A sample is a part of a
population called the
universe, reference or parent
population.
Sampling is the process or
technique of selecting a
sample of appropriate
characteristics and adequate
size
Sample frame Sample unit
ADVANTAGES
Reduces cost, time and number
Thorough investigation
Provide adequate and in-depth
coverage of sample
Efficiency
Representativeness
Measuribility
Size
Coverage
Goal orientation
Feasibility
Economy and cost
efficiency
Purposive selection Random selection
Non probability sampling
Quota sampling
Purposive sampling
Convenience sampling
Probability sampling
Simple random sampling
Systematic sampling
Stratified sampling
Cluster sampling
QUOTA SAMPLING
General composition is decided in advance
PURPOSIVE SAMPLING
 Non representative subset of some larger population
 Constructed to serve a very specific need or purpose
CONVENIENCE SAMPLING
 Is a matter of taking what you get
 It is an accidental sample
SIMPLE RANDOM SAMPLING
 Each and every unit in a population has an equal chance of
being included in the sample
 Selection of unit is by chance
Lottery method
Table of
random
numbers
SYSTEMATIC SAMPLING
 Selecting one unit at random and then additional units
at evenly spaced interval
STRATIFIED SAMPLING
 The population is first divided into subgroups or strata
according to certain common characteristics.
Stratified
random
Stratified
systematic
CLUSTER SAMPLING
 Used when the population forms natural groups or
clusters
 Villages, wards blocks or children of a school
If cluster contains
similar persons,
findings cannot be
generalized to the
parent population
Administratively
simple, less
expensive than
random sampling
Multiphase
• Part of information from
whole sample and a part
from the sub-sample
Multistage
• First stage is to select the
groups or clusters
• Then subsamples are
taken in many
subsequent stages as
necessary to obtain the
desired sample size
Sampling
error
Non sampling
error
Coverage error
Observational error
Processing error
• Deals with techniques to know how far the difference
between the estimates of different samples is due to
sampling variation or not
• Rejecting a null
hypothesis
when its true
Type 1 error
• Accepting a
null hypothesis
when its false
Type 2 error
• Probability of
rejecting a null
hypothesis
when it is false
Power
Parametric tests Non-parametric tests
t-test- paired/unpaired Mann Whitney Mc nemar’s
ANOVA Test of significance b/w
means
Wilcoxon’s signed rank test
Pearson’s Correlation Coefficient Mc nemar’s
Z-test Chi- square test
Spearman’s Rank Correlation
Freidman
Student’s t- Test
 Designed by W.S Gossett whose pen name was
student
Sample randomly selected
Quantitative data
Follow normal distribution
Sample less than 30
ANOVA Test
• Used for comparing more than two samples mean
drawn from corresponding normal populations
• One way ANOVA
• Two way ANOVA
Z Test
• The sample or the samples must be randomly selected
• The data must be quantitative
• The variable is assumed to follow normal distribution
in the population
• The sample size must be larger than 30
Chi-square Test
• Developed by Karl Pearson
• Data measured - terms of attributes/qualities- intended to
test if difference is due to sampling variation
• Involves calculation of a quantity
• 3 important applications:
1. Proportion
2. Association
3. Goodness of fit
Relationship
between two sets
of variable
Denoted by r
From -1 to +1
CORRELATION
Statistical method
for studying the
relationship
between a single
dependent variable
and one or more
independent
variables
REGRESSION
• Perfect positive correlation: The correlation co-efficient(r) =
+1 i.e. both variables rise or fall in the same proportion.
• Perfect negative correlation: The correlation co-efficient(r)
= -1 i.e. variables are inversely proportional to each other,
when one rises, the other falls in the same proportions.
• Moderately positive correlation: Value lie between 0< r< 1
• Moderately negative correlation: Value lies between -1< r<
0
• Absolutely no correlation: r = 0, indicating that no linear
relationship exits between the 2 variables
Conclusion
• The knowledge of medical statistics enables one to
develop a self- confidence & this will enable us to
become a good clinician, good medical research
worker, knowledgeable in statistical thinking
References
• Soben Peter - Essentials Of Preventive And
Community Dentirsty-sixth Edition
• Park - A Textbook Of Prventive And Social
Medicine - Nineteenth Edition
• Review of preventive and social medicine by vivek
jain
• Methods in Biostatistics- 7th edition by BK Mahajan
THANK YOU

Epidemiology and biostatistics in dentistry

  • 1.
    EPIDEMIOLOGY Presented by- Dr.Parikshit S Kadam ( JR-1)
  • 2.
    Content • Introduction • Definition •History • Aims of epidemiology • Tools of measurements • Epidemiological studies • Bias
  • 3.
    • Association andcausation • Conclusion • References
  • 4.
    Introduction • Epidemiology isthe basic science of Preventive and Social Medicine • Epidemiology is scientific discipline of public health to study diseases in the community to acquire knowledge for health care of the society
  • 5.
    • Epi –upon demos- people logos – study or science
  • 6.
    Definition • “ Thebranch of medical science which deals with treatment of epidemics” Parkin ( 1873) • “ The study of the distribution and determinants of disease frequency in man” MacMohan ( 1960)
  • 7.
    • “The studyof the distribution and determinants of health-related states or events in specified populations, and the application of this study to the prevention and control of health problems” John M. Last (1988)
  • 8.
    History • First knownepidemiologist was Hippocrates ( 460-375 B.C) • “ No disease”, he said, “is sent by evils or demons, but is the result of natural causes” • Claudius Galen (130-200 A.D) a Greek wrote that “ reason alone discovers some things; experience alone discovers some things; but to find others, requires both reason and experience”
  • 9.
    • In the17th century, Thomas Sydenham (1624-1689) a London physician, stressed the importance of careful observations • He wrote the history of disease and was called the “ Father of English medicine, or the English Hippocrates”
  • 10.
    • John Snow(1813-1858) is considered as the “ Father of Epidemiology” • Develop interest in the epidemic of cholera in London, in August 1854 • Similar study was done by William Budd (1811-1880) on typhoid fever
  • 11.
    • First dentalfield study was reported in Britain 1803 by Sir John Lincour • Collected details of the health habits and dental state of 96 old men all aged over 80 years • Edwin Saunders, a young dentist studies the eruption of teeth between ages 9 and 13 • In 1837 addressed his findings to parliament in a report entitled, “ The teeth a test of age”
  • 12.
    Aims Epidemiology • Todescribe the size and distribution of disease problems in human populations • To identify etiological factors (risk factors) in the pathogenesis of disease • To provide data essential to the planning, implementation and evaluation of health services for the prevention, control and treatment of disease and for setting priorities among those services
  • 13.
    Principles Of Epidemiology 1.Exact observation 2. Correct interpretation 3. Rationale explanation 4. Scientific construction
  • 14.
    Tools In Epidemilogy •Numerator – Number of events in a population during specified time • Denominator 1. Total population - Mid-year population - Population at risk 2. Total events 10 100
  • 15.
    • Basic toolsare 1. Rate 2. Ratio 3. Proportion
  • 16.
    • Comparison between2 same things • Numerator is the part of denominator RATE • Comparison between 2 different things • Numerator is not part of denominator RATIO • Numerator is the part of denominator PROPORTION
  • 17.
    Rate • It isthe frequency of a disease or characteristics expressed per unit size of the population or group in which it is observed • Rate = ×10n Number of events in a specific period Population at risk of experiencing the events or disease
  • 18.
    • 2000 ×1000 1. Crude rate 2. Specific rate 3. Standardized rate 5000
  • 19.
    Ratio • “It expressesa relation in size between two random quantities, in this numerator is not a component of the denominator” • x : y or x y
  • 20.
    Proportion • A proportionis a ratio which expresses the relation in magnitude of a part of the whole • Numerator always a part of denominator
  • 21.
    Measurements in Epidemiology •Measurement of MORTALITY • Measurement of MOBIDITY • Measurement of DISABILITY • Measurement of NATALITY • Measurement of presence, absence or distribution of the characteristics or attributes of the disease
  • 22.
    • Measurements ofmedical needs, health care facilities, utilization of health care services and other health related events • Measurement of presence, absence or distribution of the environment and other factors suspected of causing the disease • Measurement of demographic variables
  • 23.
    Measurement of MORTALITY •Mortality is an integral part of demography • Many countries have routine systems for collecting mortality data. Traditionally and universally, most epidemiological studies begin with mortality data
  • 24.
    Problems The incomplete reporting of deaths Lack of accuracy Lackof uniformity Choosing a single cause of death
  • 25.
    Uses • In indicatingpriorities for health action • Allocation of resources, In designing intervention programmes, And in the assessment and monitoring of public health programmes
  • 26.
    Mortality rates 1. Crudedeath rate :- “ the number of deaths per 1000 people in a population in a given year ” Crude death rate = No. of death during the year in a population Mid-year population
  • 27.
    2 . Specificdeath rate:- A specific death rates measures the number of deaths among people in a category per 1000 people in that category in a given year Specific death rate = No. of deaths due to cause Mid-year population
  • 28.
    3. Age-specific deathrate:- Death rate specific to a given age group 4. Case fatality rate :- Represents the killing power of a disease 5. Proportional mortality rate :- The number of deaths due to a particular cause in a specific age groups per 100 or 1000 total deaths
  • 29.
    6. Standardized rates:-The overall rates adjusted for the affects of differences in population composition
  • 30.
    Factors affecting mortalityrate • Birth rate • Density of population • Geographical • Season • Epidemic experience • Secular variation
  • 31.
    MEASUREMENT OF MORBIDITY ‘Morbidity’ as “any departure, subjective or objective, from a state of physiological well being ’’. Linenfeid A M.,Linenfeid D E. Foundation of epidemiology 1990
  • 32.
    Uses Describe the extent and natureof the disease Provide more comprehensive and more accurate and clinically relevant information Serve as starting point for etiological studies Needed for monitoring and evaluation of disease control activities
  • 33.
    Incidence • The numberof new cases occurring in a defined population during a specified period of time • It refers to 1. Only to new cases 2. During a given period 3. In a specified population or population at risk
  • 34.
    • Incidence rate= ×1000 Number of new cases of a specific disease during given time period The population at risk Episode Cumulative
  • 35.
    • when thepopulation is exposed to risk for a limited period of time such as in epidemic Attack rate • The number of exposed persons developing the disease within the range of incubation period, following exposure to the primary case Secondary attack rate
  • 36.
    Uses Gives clues to researchinto the etiology and pathogenesis of disease Study of distribution of disease Helps in taking action to control disease Useful in evaluating the efficacy of preventive and therapeutic measures
  • 37.
    Prevalence • The totalnumber of all current cases (old+new) existing at a given point in time, or over a period of time in given population Point prevalence Period prevalence
  • 38.
    • Uses ofprevalence rate is  Useful in estimating the magnitude of disease or health problems of community  Helpful in identifying the potential high – risk population  Useful in administrative and planning purposes like assessing manpower needs in health services, delivery of health services etc.
  • 39.
    Longer duration ofthe disease Prolongation of life of patient Increase in new cases In-migration cases Out-migration of healthy patients Improved diagnostic facilities Shorter duration of the disease High case-fatality rate from disease Decrease in new cases In-migration of healthy people Out-migration of cases Improved cure rate of cases
  • 40.
    Incidence Prevalence Numerator Numberof new cases of disease during specific period of time Number of existing cases of disease at a given point of time Denominator Population at risk Population at risk Focus Whether the event is a new case Time of onset of the disease Presence or absence of a disease Time period is arbitrary Uses Express the risk of becoming ill To study acute disease Useful for studies of causation Estimate the probability of a population being ill at the period of time being studied Useful for study of chronic disease and implication of health services
  • 41.
    RELATION BETWEEN PREVALENCE &INCIDENCE • Prevalence depends upon two factors, the incidence & duration of illness • Prevalence = Incidence × Mean duration P = I × D
  • 42.
  • 43.
    DESCRIPTIVE EPIDEMIOLOGY • Asimple description of the health status of a community • Based on routinely available data or data obtained in special surveys • Is often the first step in an epidemiological investigation
  • 44.
    Formulating an etiologicalhypothesis Comparing with known indices Measurement of the disease Describing the disease in terms of Time Place Person Defining the disease under study Defining the population to be studies
  • 45.
    1. Defining populationto be studied • It is a ‘Population study’ not of an individual • Defining population by total number and composition (age, sex, occupation etc. ) • Defined population- can ‘whole population’or ‘a representative sample’ • It provides ‘denominator’ for calculating rates and frequency
  • 46.
    2. Defining diseaseunder study • Operation Definition - of disease is essential for measuring the disease in defined population • ‘Case definition’ should be adhered throughout the study
  • 47.
    3. Describing disease TimeYear, Month, Week, Season, Duration Place Country, Region, Climatic zone, Urban/rural, Community, Cities, Towns Person Age, Sex, Marital status, Occupation, Education, Socioeconomic status
  • 48.
    Time distribution Short-term Common source Single exposure or point source Continuousor multiple exposure Propagated epidemics Person to person Arthropod vectors Animal reservoir Periodic Seasonal Cyclic trends Long-term
  • 49.
    Place distribution • Variationin frequency of different disease manifestation from place to place has long been organized • The distribution of disease according to places can be classified as • International variation • National variation • Rural – Urban variation • Local variation/ distributions
  • 50.
    INTERNATIONAL VARIATION • Examinemortality and morbidity in relation to socioeconomic factors, dietary differences and difference in culture and behaviour • Ex : Oral cancer has highest incidence in countries like India , Bangladesh, Srilanka & Pakistan . • Breast cancer shows highest prevalence in the countries of the western world like Netherlands , England and Wales • Britain has highest rates for lung cancer
  • 51.
    NATIONAL VARIATION • Variationin disease occurs in the same country • Ex : In India endemic goiter, malaria, fluorosis, leprosy with some parts of country more affected & other parts less affected or not affected at all RURAL – URBAN VARIATION • It is a well established fact that health and disease are not equally distributed in urban and rural population • Chronic bronchitis, lung cancer, CVS disease - common in urban areas • Skin and zoonotic infections - in rural areas
  • 52.
    LOCAL DISTRIBUTER • Thepreparations of maps showing the distribution of cases of a disease within the local community is a long established epidemiologic procedures • ‘Spot maps’ or ‘shaded maps’ are used to study the variations in disease frequency • Eg. If map show clustering of cases it may suggest common source of infection
  • 53.
    Migration study • Itis of two types; • Comparing the rate of occurrence of disease and the death rate for migrants with those if their same group who have stayed at home • Comparing the migrants with the local population of the host country provides valuable information on the genetically different groups living in a similar environment • Anderson M. An introduction to epidemiology. 2nd edition
  • 54.
    • PERSON DISTRIBUTION •In descriptive studies, disease is further characterized by defining the person who developed disease 1. Age : • It is variable and must always be considered in epidemiologic study • Certain disease are more prevalent in specific age group • Measles – children • Cancer – middle age • Atherosclerosis – old age
  • 55.
    2 . SEX •Chronic conditions are more common in females like thyrotoxicosis, diabetes mellitus, obesity, arthritis etc • In Males, diseases include peptic ulcer, respiratory cancer, lung cancer etc
  • 56.
    3. Ethnic groups/ Ethnicity • Can be identified in terms of race , religion , place of birth or combination of three • Examples :Dental caries-western countries, Periodontal disease - in Blacks 4. Occupation - Alter the habit pattern of employee like sleep, alcohol, smoking - for identification of risk associated with exposure to chemicals, physical , biologic agents peculiar to certain occupations
  • 57.
    5. Socioeconomic status •It has different meanings for different persons , income , living conditions, occupation, education and social prestige • The individuals belonging to the upper social classes exhibit a longer life expectancy and better health and nutritional state than the individuals belonging to lower social classes
  • 58.
    6. Marital status •Marital is a descriptive variable that appears on medical, dental and civil records almost as regularly as age and sex • The married persons have lower mortality rates from nearly all causes of death , than the single ,widowed or divorced person
  • 59.
    4. Measurement ofdisease • To obtain the clear picture of ‘disease load’ in the population • In terms of Mortality, Morbidity and Disability • Morbidity has two aspects – - Incidence – Longitudinal Studies - Prevalence - Cross-sectional studies
  • 60.
    5. Comparing withknown indices • Basic epidemiological approach – 1. making comparisons 2. Asking questions • Making comparison with known indices in population • By making comparisons - clues about - Disease etiology - High risk population
  • 61.
    6. Formulation ofetiological hypothesis • A hypothesis is supposition arrived at observation or reflection • Hypothesis should specify – 1. Population 2. Specific cause – risk factors/exposures 3. Outcome – disease/disability 4. Dose-response relationship 5. Time response relationship Smoking 40-50 beedis per day, will result in leukoplakia among 4% of beedi smokers after 10 years
  • 62.
    Uses of DescriptiveEpidemiology 1. Provide data of magnitude of problem- disease load 2. Provide clues for etiology 3. Provide background data for planning, organizing and evaluating the preventive and curative services 4. Contributes to research
  • 63.
    Analytical Studies • Analyzingrelationships between health status and other variables • The objective is testing the hypothesis • Subject of interest is individual, but inference applied to population • TYPES 1. Case-control studies(Case reference studies) 2. Cohort studies (Follow-up studies)
  • 64.
    Case-control studies • Itis first approach to testing causal hypothesis, • Especially for rare disease • Three features:- 1. Both exposure and outcome (disease) has occurred 2. Study proceeds backwards from effect to cause 3. It uses a control group to support or refuse a inference
  • 65.
  • 66.
    • Basic stepsin Case-control study:- 1. Selection of cases and controls 2. Matching 3. Measurement of exposure 4. Analysis and interpretation
  • 67.
    1. Selection ofcases and controls • CASES – - Case definition – (Diagnostic criteria and Eligibility criteria) - Source of Cases – (Hospital or General population)
  • 68.
    • CONTROLS - Freefrom the disease under study - Similar to the cases in all other aspects • Sources:- Hospital, Relative, Neighbourhood, General population
  • 69.
    2. Matching • Matchingis process by we selecting controls in a manner that they are similar to cases in all variables • Matching is essential for comparability and for elimination of confounding bias
  • 70.
    • A Confoundingfactor is a factor which associated with both exposure and disease and unequally distributed in study and control groups • Matching procedure – - Group matching (Strata matching) - Pair matching
  • 71.
    3. Measurement ofexposure • Information of exposure of risk factor should be obtain in same manner for both cases and controls • Information obtain by:- - Questionnaire - Interviews - Hospital records - Employment records
  • 72.
    4. Analysis andinterpretation 1. Exposure rates:- Estimation of rates of exposure of suspected factor among cases & controls 2. Odds Ratio:- Estimation of disease risk associated with exposure among cases & controls
  • 73.
    1. Exposure rates CASES(Lung Cancer) CONTROLS (Without Lung Cancer) TOTAL SMOKERS 33 (a) 55 (b) 88 (a+b) NON- SMOKERS 2 (c) 27 (d) 29 (c+d) TOTAL 35 (a+c) 82 (b+d) N= a+b+c+d
  • 74.
    2. Odds Ratio •It is estimation of risk of disease associated with exposure • It measures strength of association of risk factor and outcome(disease) • Odds Ratio = 33 x 27 / 55 x 2 = 8.1 • Smokers have risk of developing lung cancer 8.1 times higher than non-smoker ODDS RATIO = AD/BC
  • 75.
    Cohort Studies • Alsoknown as prospective study, longitudinal study, incidence study, forward looking study • Cohort is group of people with similar characteristics • Begin with a group of people who are free of disease. • Whole cohort is followed up to see the effect of exposure
  • 76.
    Population Non-exposed Exposed Time Direction of inquiry People withoutthe disease Disease No disease Disease No disease
  • 77.
    • Types ofCohort Studies:- 1. Prospective cohort studies 2. Retrospective cohort studies 3. Combination of retrospective and prospective cohort studies
  • 78.
    Elements of Cohortstudies 1. Selection of study subjects 2. Obtaining data on exposure 3. Selection of comparison group 4. Follow-up 5. Analysis
  • 79.
    1. Selection ofstudy subjects • General population or • Special group (Doctors, Teachers, Lawyers) • Cohort should be selected from the group with special exposure under study
  • 80.
    2. Obtaining dataon exposure a. Cohort members- questionnaire, interview b. Review of records c. Medical Examination or tests d. Environmental surveys
  • 81.
    • Categorized accordingto exposure – 1. Whether exposed or not exposed to special causal factor 2. Degree of exposure
  • 82.
    3. Selection ofcomparison group • Subjects are categorized in group according to degree of exposure & mortality and morbidity compared Internal comparison • When degree of exposure not known • Control group with similar in other variable External comparison • Comparison with the general population as exposed group Comparison with general population
  • 83.
    4. Follow-up • Regularfollow-up of all participants • Measurement of variable depends upon outcome • Procedure:- 1. Periodical medical examination 2. Review of hospital records 3. Routine surveillance and death records 4. Mailed questionnaire and phone calls
  • 84.
    5. Analysis • Dataare analyzed in terms of :– a. Incidence rates- Among exposed and non-exposed b. Estimation of risk.:- 1. Relative Risk 2. Attributable Risk
  • 85.
    Incidence rates SMOKING DEVELOP EDLUNG CANCER NOT DEVELOP ED LUNG CANCER TOTAL YES 70 (a) 6930(b) 7000 (a+b) NO 3(c) 2997 (d) 3000 (c+d)
  • 86.
    Relative Risk • Relativerisk is the ratio of the incidence of disease among exposed and incidence among non-exposed • It is direct measure of strength of the association between suspected cause and effect
  • 87.
    Attributable Risk • ARis the difference in incidence rates of disease among exposed and non-exposed group • AR= I.R. among exposed - I.R. among non-exposed I Incidence among exposed x100 • AR is the proportion of disease due to particular risk factor exposure • That means- amount of disease eliminated if the suspected risk factor is removed
  • 88.
    Population Attributable Risk •Population A. R. = I.R. in total population – I.R. among non- exposed I.R. in total population X 100 • Population Attributable Risk is useful concept as it give the magnitude of disease that can be reduced from the population if the suspected risk factor is eliminated or modified
  • 89.
    Exposure and outcome ExposureOutcome Remarks Direction Prospective cohort study Occurred Followed- up Start with exposure Forward looking Retrospective cohort study Occurred Occurred Start with exposure Forward looking Mixed cohort study Occurred Occurred Start with exposure Forward looking Case control study Occurred Occurred Start with outcome Backward looking Cross-sectional study Occurred Occurred Both exposure and outcome assesed Neither forward nor backward looking
  • 90.
    Case control Cohort Startswith the disease, proceeds from effect to cause Starts with the people exposed to the risk factor, proceeds from cause to effect It is first approach to test a hypothesis Reserved for testing precisely formulated hypothesis Involves fewer subjects Involves large number of subjects Yields results quickly Results are delayed due to long follow up periods Suitable for studying rare diseases unsuitable Gives relative risk Gives relative risk and attributed risk Inexpensive Expensive
  • 91.
    Characteristics Cross-sectional Case-controlCohort study Time One time point Retrospective Prospective Other names Prevalence study Case reference study Longitudinal study Forward looking study Follow up study Incidence study Incidence No No Allows Prevalence Allows No No Casuality No Yes Yes Role of disease Measures disease Begin with disease End with disease Assesses Association of risk factors and disease Many risk factors for single disease Single risk factor affecting many diseases Data anlaysis Chi-square to assess association Odds ratio to estimate risk Provide direct estimate of relative risk Advantages Used to calculate prevalence Faster Quick and inexpensive Useful to study rare diseases Require few subjects Easy to conduct Incidence can be calculated Provides direct estimate of relative risk Disadvantages Unusable for acute diseases Recall bias and selection bias are present Miss the undiagnosed or asymptomatic cases Expensive Time consuming Involves large number of subjects
  • 92.
    EXPERIMENTAL EPIDEMIOLOGY • Interventionalor experimental study involves attempting to change a variable in subjects under study • The effects of an intervention are measured by comparing the outcome in the experimental group with that in a control group
  • 93.
    Objectives of ExperimentalStudies 1. To provide ‘scientific proof’ for etiology of disease and risk factor which may allow modification of occurrence of disease 2. To provide a method of measurement for effectiveness and efficiency of therapeutic / preventive measure for disease 3. To provide method to measurement for the efficiency health services for prevention, control and treatment of disease
  • 94.
    Types of ExperimentalStudies 1. Randomized Control Trials 2. Field Trials & Community Trials
  • 95.
    Randomized Control Trials •RCT is a planned experiment designed to asses the efficacy of an intervention in human beings by comparing the effect of intervention in a study group to a control group • The allocation of subjects to study or control is determined purely by chance (randomization) • For new programme or new therapy RCT is best method of evaluation
  • 96.
    Basic Steps inRCT 1. Drawing-up a protocol 2. Selecting reference and experimental population 3. Randomization 4. Manipulation or Intervention 5. Follow-up 6. Assessment of outcome
  • 97.
    The Protocol • Studyconducted under strict protocol • Protocol specifies :- aim, objectives, criteria for selection of study and control group, sample size, intervention applied, standardization and schedule and responsibilities
  • 98.
    Reference and Experimental population •Reference population (Target Population) • Is the population in which the results of the study is applicable • A reference population may be – Human being, country, specific age, sex, occupation etc.
  • 99.
    • Experimental Population(Study Population) • It is derived from the target population • Three criteria:- 1. They must be representative of RP 2. Qualified for the study 3. Ready to give informed consents
  • 100.
    Randomization • It isstatistical procedure to allocate participants in groups – Study group and Control group • Randomization gives equal chance to participants to be allocated in Study or Control group • Randomization is an attempt to eliminate ‘bias’ and allow ‘comparability’
  • 101.
    • Randomization eliminates‘Selection Bias’ • Matching is for only those variable which are known • Randomization is best done by the table of random numbers • In Analytical study there is no randomization, we already study the difference of risk factor. So only option is Matching
  • 102.
    Manipulation or Intervention •Manipulation by application of therapy or reduction or withdrawal of suspected causal factor in Study and control group • This manipulation creates independent variable whose effect is measured in final outcome
  • 103.
    Follow-up • Follow-up ofboth study and control group in standard manner in definite time period • Duration of trial depends on the changes expected in duration since study started • Some loss of subjects due to migration, death is k/as Attrition
  • 104.
    Assessment • Final stepis assessment of outcome in terms of positive and negative results • The incidence of positive and negative results are compared in both group- Study group and Control group • Results are tested for statistical significance (p value)
  • 105.
    Study designs • Concurrentparallel study design • Cross-over type of study design
  • 106.
    Field trials • Fieldtrials, in contrast to clinical trials, involve people who are healthy but presumed to be at risk • Data collection takes place “in the field,” usually among non-institutionalized people in the general population • Since the subjects are disease-free and the purpose is to prevent diseases
  • 107.
    Community Trials • Inthis form of experiment, the treatment groups are communities rather than individuals • This is particularly appropriate for diseases that are influenced by social conditions, and for which prevention efforts target group behaviour
  • 108.
    Clinical trials • PhaseI – Human pharmacology and safety • Phase II – Therapeutic exploration and dose ranging • Phase III – Therapeutic conformation • Phase IV – Post marketing surveillance
  • 110.
    Potential errors inepidemiological studies • Bias may arise from the errors of assessment of outcome due to human element • Apprehension • Attention (Hawthorne effect) • Berksonian bias • Recall bias • Neyman bias
  • 111.
    Bias in cohortstudies Selection bias Information bias Confounding bias Post hoc bias Bias in control studies Berkesonian bias Recall bias Telescoic bias Interviewer’s bias Bias due to confounding Prevalence incidence bias Bias in RCT Subject variation Observer bias Investigator bias Others Hawthorne bias Pygmalion effect
  • 112.
    Blinding • Single blinding •Double blinding • Triple blinding
  • 113.
    Association and causation 1.Causal association • Direct causal association • Indirect causal association 2. Non-causal association
  • 114.
    Conclusion • Epidemiological researchcan be particularly useful in promoting public health because it provides evidence to enable the public health practitioners to identify priorities and explore the risk factors
  • 115.
    References • Soben Peter- Essentials Of Preventive And Community Dentirsty-sixth Edition • Park - A Textbook Of Prventive And Social Medicine - Nineteenth Edition • Review of preventive and social medicine by vivek jain
  • 116.
  • 117.
    BIOSTATISTICS Presented by- Dr.Parikshit Kadam ( JR-1)
  • 118.
    CONTENTS • Introduction • Categoriesof research • Scientific methods • Definition • Uses of biostatistics • Common statistical terms • Sources and collection of Data • Presentation of Data • Analysis and interpretation
  • 119.
    • Statistical averages •Measures of Dispersion • Sampling and sampling methods • Sampling errors • Tests of significance • Correlation and regression • Conclusion • References
  • 120.
    • The wordstatistics comes from the italian word “statista” meaning “statesman” or the german word “statistik” which means a political state. • John Graunt(1620-1674) – Father of health statistics
  • 121.
    Statistics is thescience of compiling, classifying and tabulating numerical data and expressing the results in a mathematical or graph form Biostatistics is that branch of statistics concerned with mathematical facts and data related to biological events
  • 122.
    • We, medicaland dental students during period of our study, learn best methods of diagnosis and therapy • After graduation, we go through research papers presented at conferences and in current journals to know new methods of therapy, improvement in diagnosis and surgical techniques • It must be admitted that essence of papers contributed to medical journals is largely statistical
  • 123.
    • Training instatistics has been recognized as “indispensible” for students of medical science • For eg. if we want to establish cause and effect relationship, we need statistics • If we want to measure state of health and also burden of disease in community, we need statistics
  • 124.
    • Statistics arewidely used in epidemiology, clinical trial of drug vaccine, program planning, community medicine, health management, health information system etc. • The knowledge of medical statistics enables one to develop a self- confidence & this will enable us to become a good clinician, good medical research worker, knowledgeable in statistical thinking
  • 125.
    • Everything inmedicine, be it research, diagnosis or treatment depends on counting or measurement • According to Lord Kelvin, when you can measure what you are speaking about and express it in numbers, you know something about it but when you can not measure, when you can not express it in numbers, your knowledge is of meagre and unsatisfactory kind
  • 126.
    • In PublicHealth or Community Health, it is called Health Statistics • In Medicine, it is called Medical Statistics. In this we study the defect, injury, disease, efficacy of drug, serum and line of treatment, etc. • In population related study it is called Vital Statistics. e.g. study of vital events like births, marriages and deaths
  • 127.
  • 128.
    BASIC V/S APPLIED •Basic research is usually considered to involve a search for knowledge without a defined goal of utility or specific purpose • Applied research is problem-oriented, and is directed towards the solution of an existing problem
  • 129.
    OBSERVATIONAL V/S EXPERIMENTAL • Observational– to observe things happening without interfering with it • Experimental – manipulating some aspect of environment and observing its effects
  • 130.
    QUALITATIVE V/S QUANTITATIVE • Qualitativeresearch – deals with subjective aspects • Quantitative research – based on measurement of quantity or amount (objective aspects )
  • 131.
    CONCEPTUAL V/S EMPIRICAL •Conceptual – related to some abstract idea or theory • Empirical – experience or observation alone are the tools of research (data based research )
  • 132.
    PPRIMARY & SECONDARY RESEARCH •PRIMARY RESEARCH- first hand reports of facts or findings • SECONDARY RESEARCH- from primary research 132
  • 133.
  • 134.
    DEFINITIONS • American HeritageDictionary defines statistics as: "The mathematics of the collection, organization, and interpretation of numerical data, especially the analysis of population characteristics by inference from sampling” • The Merriam-Webster’s Collegiate Dictionary definition is: "A branch of mathematics dealing with the collection, analysis, interpretation, and presentation of masses of numerical data"
  • 135.
    • A Simplebut Concise definition by Croxton and Cowden: “Statistics is defined as the Collection, Presentation, Analysis and Interpretation of numerical data” • “Statistics defined as the science of  Collection  Organisation  Presentation  Analysis and interpretation of numerical data”
  • 136.
    Test difference is realor chance Study the correlation Evaluate the efficacy of vaccines, sera Measure mortality and morbidity Evaluate achievements of public health programs Help promote health legislation and create administrative standards for oral health
  • 137.
    Common statistical terms •Variable:- A characteristic that takes on different values in different persons, places/ things • Constant:- Quantities that do not vary such as π = 3.141, e = 2.718. These do not require statistical study. In Biostatistics, mean, standard deviation, standard error, correlation coefficient and proportion of a particular population are considered constant • Observation:- An event and its measurement. for eg.. BP and its measurement
  • 138.
    • Observational unit:-The “sources” that gives observation for eg. Object, person etc. in medical statistics:- terms like individuals, subjects etc are used more often • Data :- A set of values recorded on one or more observational units • Population:- It is an entire group of people or study elements persons, things or measurements for which we have an interest at particular time • Sampling unit:- Each member of a population • Sample:- It may be defined as a part of a population
  • 139.
    • STATISTIC/ DATUM:-Measured/ counted fact or piece of information such as height of person, birth weight of baby • STATISTICS/ DATA:- Plural of the same such as height of 2 persons, birth weight of 5 babies, plaque score of 3 person • BIOSTATISTICS:- Term used when tools of statistics are applied to the data that is derived from biological sciences such as medicine
  • 140.
    • Demographic datacomprises of population size, geographic distribution, ethnic groups, socio economic factors and their trends over time. Such data are obtained from census/ surveys, experiments, hospital records and other public service reports and are important determinants for oral health care programs
  • 141.
  • 142.
  • 143.
  • 144.
    • Main sourcesfor collection of medical statistics: 1. Experiments 2. Surveys 3. Records • Experiments and surveys are applied to generate data needed for specific purposes • While Records provide ready- made data for routine and continuous information
  • 145.
    Methods of collectionof data • Method of direct observation:- Clinical signs and symptoms and prognosis are collected by direct observation • Method of house to house visit:- Vital statistics and morbidity statistics are usually collected by visiting house to house • Method of mailed questionnaire:- This method is followed in community where literacy status of people is very high
  • 146.
    Tabulation Master table Simple table Frequencydistribution table Chartsanddiagrams Bar chart Pie diagram Line diagram Histogram frequency polygon Cartogram Pictogram Scatter diagram
  • 147.
    Tabulation • As simpleas possible • Data must be according to size or importance, chronologically or alphabetically • Should be self-explanatory • Each row and column labelled concisely and clearly • Title should be clear, concise and to the point and it should be separated from body of the table by lines or spaces
  • 148.
    Simple Table States Population1st march 2011 Andhra pradesh 8,46,65,533 Madhya pradesh 7,25,97,565 Uttar pradesh 19,95,81,477 Karnataka 7,14,83,435 Rajasthan 18,23,45,998 kerela 6,43,35,772
  • 149.
    Frequency distribution table •The following figures are the ages of patients admitted to a hospital with poliomyelitis.. 8, 24, 18, 5, 6, 12, 14, 3, 23, 9, 18, 16, 1, 2, 3, 5, 11, 13, 15, 9, 11, 11, 7, 106, 9, 5, 16, 20, 4, 3, 3, 3, 10, 3, 2, 1, 6, 9, 3, 7, 14, 8, 1, 4, 6, 4, 15, 22, 2, 1, 4, 6, 4, 15, 22, 2, 1, 4, 7, 1, 12, 3, 23, 4, 19, 6, 2, 2, 4, 14, 2, 2, 21, 3, 2, 1, 7, 19 Age Number of patients 0-4 35 5-9 18 10-14 11 15-19 8 20-24 6
  • 150.
    Attractive to eyes Givea bird’s eye view of entire data Lasting impression Facilitate comparison of data
  • 151.
    Title self explanatory Simple and consistent Valueson x-axis and frequency on y-axis Few lines drawn in graphs Scale of presentation mentioned Scale of division proportional
  • 152.
    Quantitative data • Histogram • Frequencypolygon • Frequency curve • Line chart or graph • Cumulative frequency diagram • Scatter diagram Qualitative data • Bar diagram • Pie or sector diagram • Pictogram • Map diagram
  • 154.
  • 155.
  • 156.
  • 157.
    Biostatistics 157 Cumulative FrequencyDiagram 25 35 40 45 55 70 90 0 10 20 30 40 50 60 70 80 90 100 0 to 10 yrs 10 to 20 yrs 20 to 30 yrs 30 to 40 yrs 40 to 50 yrs 50 to 60 yrs 60 to 70 yrs Prevalence of Dental Caries ( in percent)
  • 158.
    Biostatistics 158 Scatter orDot diagram 0 2 4 6 8 10 12 14 0 5 10 15 Carious lesion Sugar Exposure
  • 159.
    Bar chart • Lengthof bars drawn vertical or horizontal is proportional to frequency of variable • Suitable scale is chosen • Bars usually equally spaced
  • 160.
    Biostatistics 160 Bar chart •They are of three types - Simple bar chart - Multiple bar chart • Two or more variables are grouped together - Component bar chart • Bars are divided into two parts • Each part representing certain item and proportional to magnitude of that item
  • 161.
    Biostatistics 161 Simple barchart 0 50 100 150 200 250 300 1st Qtr 2nd Qtr 3rd Qtr 4th Qtr Number of CD Patients
  • 162.
    Biostatistics 162 Multiple barchart 250 320 45 180 370 80 220 280 95 290 390 40 0 50 100 150 200 250 300 350 400 1st Qtr 2nd Qtr 3rd Qtr 4th Qtr CD Patients RPD Patients FPD Patients
  • 163.
    Biostatistics 163 Component barchart 1500 1850 1400 2100 300 450 200 500 0 500 1000 1500 2000 2500 3000 1st Qtr 2nd Qtr 3rd Qtr 4th Qtr Patients to prostho Patients to other Departments
  • 164.
    Biostatistics 164 Pie chart 200,31% 150, 24% 180, 29% 70, 11% 30, 5% PROSTHO CONSO PERIO ORTHO PEDO
  • 167.
  • 168.
    • Is collectionof units of observation that are of interest and is the target of investigation
  • 169.
    • It isa state, condition, concept or event whose value is free to vary within the population • A variable is an attribute that describes a person, place or thing Qualitative (categorical) Quantitative (numerical)
  • 170.
    Variables Categorical Nominal Categories are mutually exclusive and unordered e.g– gender,blood group Ordinal Categories are mutually exclusive but ordered e.g- stage of disease, pain score(mild/mod erate severe) Numerical Discrete Integer, values or counts e.g – no. of teeth with caries Continuous Any value in a range of values- e.g weight in kgs, height in cms
  • 171.
  • 172.
    • P- valueis defined as the probability under the assumption of null hypothesis of obtaining a result equal to or more extreme than that was actually observed Binominal distribution • Two parameters • Occurs when a fixed number of subjects • Characteristic is dichotomous in nature • P or 1-p Normal distribution • Mathematical curve represented by two quantities m and s
  • 173.
    Should be easyto understand and compute Should be based on each and every item in series Should not be affected by extreme observations Sampling stability PROPERTIES
  • 174.
    MEAN • Simplest measure MEDIAN • Middlevalue MODE • Occurs with greatest frequency Mode = 3 Median – 2 Mean
  • 175.
    • For eg..the income of 7 people per day in rupees are as follows. 5, 5, 5, 7, 10, 20, 102= (total 154) • Mean = 154/7 = 22 • Median= 7 • Median, therefore, is a better indicator of central tendency when more of the lowest or the highest observations are wide apart • Mode is rarely used as series can have no modes, 1 mode or multiple modes
  • 176.
    Measures of Dispersion •Widely known measures of dispersion are a. The Range b. The Mean or Average Deviation c. The Standard Deviation • Range : Simplest difference between highest and lowest figures for eg.. Diastolic BP – 83, 75, 81, 79, 71, 90, 75, 95, 77, 94 so, the range is expressed as 71 to 95 or by actual difference of 24
  • 177.
    Mean deviation • Itis the summation of difference or deviations from the mean in any distribution ignoring the + or – sign • Denoted by MD MD = € ( x – x ) n X = observation X = mean n = no of observation
  • 178.
    Standard deviation • Alsocalled root mean square deviation • It is an improvement over mean deviation used most commonly in statistical analysis • Denoted by SD or s for sample and σ for a population • Denoted by the formula SD = € ( x – x )2 n or n-1
  • 179.
    Coefficient of variation •It is used to compare attributes having two different units of measurement e.g. height and weight • Denoted by CV CV = SD X 100 Mean and is expressed as percentage
  • 180.
    Bell shaped Perfectly symmetrical Totalarea of curve is one, mean is zero and standard deviation one All three measures of central tendency coincide
  • 182.
    A sample isa part of a population called the universe, reference or parent population. Sampling is the process or technique of selecting a sample of appropriate characteristics and adequate size Sample frame Sample unit
  • 183.
    ADVANTAGES Reduces cost, timeand number Thorough investigation Provide adequate and in-depth coverage of sample
  • 184.
  • 185.
  • 186.
    Non probability sampling Quotasampling Purposive sampling Convenience sampling Probability sampling Simple random sampling Systematic sampling Stratified sampling Cluster sampling
  • 187.
  • 188.
    PURPOSIVE SAMPLING  Nonrepresentative subset of some larger population  Constructed to serve a very specific need or purpose
  • 189.
    CONVENIENCE SAMPLING  Isa matter of taking what you get  It is an accidental sample
  • 190.
    SIMPLE RANDOM SAMPLING Each and every unit in a population has an equal chance of being included in the sample  Selection of unit is by chance Lottery method Table of random numbers
  • 191.
    SYSTEMATIC SAMPLING  Selectingone unit at random and then additional units at evenly spaced interval
  • 192.
    STRATIFIED SAMPLING  Thepopulation is first divided into subgroups or strata according to certain common characteristics. Stratified random Stratified systematic
  • 193.
    CLUSTER SAMPLING  Usedwhen the population forms natural groups or clusters  Villages, wards blocks or children of a school If cluster contains similar persons, findings cannot be generalized to the parent population Administratively simple, less expensive than random sampling
  • 194.
    Multiphase • Part ofinformation from whole sample and a part from the sub-sample Multistage • First stage is to select the groups or clusters • Then subsamples are taken in many subsequent stages as necessary to obtain the desired sample size
  • 195.
  • 196.
    • Deals withtechniques to know how far the difference between the estimates of different samples is due to sampling variation or not • Rejecting a null hypothesis when its true Type 1 error • Accepting a null hypothesis when its false Type 2 error • Probability of rejecting a null hypothesis when it is false Power
  • 197.
    Parametric tests Non-parametrictests t-test- paired/unpaired Mann Whitney Mc nemar’s ANOVA Test of significance b/w means Wilcoxon’s signed rank test Pearson’s Correlation Coefficient Mc nemar’s Z-test Chi- square test Spearman’s Rank Correlation Freidman
  • 198.
    Student’s t- Test Designed by W.S Gossett whose pen name was student Sample randomly selected Quantitative data Follow normal distribution Sample less than 30
  • 199.
    ANOVA Test • Usedfor comparing more than two samples mean drawn from corresponding normal populations • One way ANOVA • Two way ANOVA
  • 200.
    Z Test • Thesample or the samples must be randomly selected • The data must be quantitative • The variable is assumed to follow normal distribution in the population • The sample size must be larger than 30
  • 201.
    Chi-square Test • Developedby Karl Pearson • Data measured - terms of attributes/qualities- intended to test if difference is due to sampling variation • Involves calculation of a quantity • 3 important applications: 1. Proportion 2. Association 3. Goodness of fit
  • 202.
    Relationship between two sets ofvariable Denoted by r From -1 to +1 CORRELATION Statistical method for studying the relationship between a single dependent variable and one or more independent variables REGRESSION
  • 203.
    • Perfect positivecorrelation: The correlation co-efficient(r) = +1 i.e. both variables rise or fall in the same proportion. • Perfect negative correlation: The correlation co-efficient(r) = -1 i.e. variables are inversely proportional to each other, when one rises, the other falls in the same proportions. • Moderately positive correlation: Value lie between 0< r< 1 • Moderately negative correlation: Value lies between -1< r< 0 • Absolutely no correlation: r = 0, indicating that no linear relationship exits between the 2 variables
  • 204.
    Conclusion • The knowledgeof medical statistics enables one to develop a self- confidence & this will enable us to become a good clinician, good medical research worker, knowledgeable in statistical thinking
  • 205.
    References • Soben Peter- Essentials Of Preventive And Community Dentirsty-sixth Edition • Park - A Textbook Of Prventive And Social Medicine - Nineteenth Edition • Review of preventive and social medicine by vivek jain • Methods in Biostatistics- 7th edition by BK Mahajan
  • 206.

Editor's Notes

  • #142 A discrete variable is characterized by gaps or interruptions in the values that it can assume. For example: - The number of daily admissions to a general hospital, - The number of decayed, missing or filled teeth per child in an elementary school continuous variable can assume any value within a specified relevant interval of values assumed by the variable. For example: - Height, - weight, - skull circumference. No matter how close together the observed heights of two people, we can find another person whose height falls somewhere in between.
  • #143 Primary sources:- here data is obtained by the investigator himself. This is first hand information. Secondary sources:- The data already recorded is utilized to serve the purpose of the objective of study eg. records of OPD of dental clinics.
  • #147 o sort and classify data into groups or classification. • Objective :- to make data simple, concise, meaningful, intresting, helpful for further analysis. Master table:- contains all the data obtained from a survey. b. Simple table:- oneway table which supply answers to questions about one characteristics only. c. Frequency distribution table:- data is first split up into convenient groups and the number of items which occur in each group is shown in adjacent columns.
  • #154 Bar diagram without gap between the bars. It s a pictorial diagram of frquency distribution. It is used to deplict quantitive data of continuous type. On the x axis the size of observatin is mared on the y axis frequencies are marked.
  • #155 Used to reperesent frequency distribution of quantitive data and useful to compare two or more frequency distribution.
  • #156 When the no of observations are very large and group interval is reduced, the frequency polygon tends to loose its angulation giving place to a smooth curve known as frequency curve.
  • #157 Useful to study the changes of vslues in the variable over a time and is simplest type of diagram.
  • #159 Shows the relationship between two quantities.
  • #177 Merit :- simplest. • Demerit :not of much practical importance. indicates nothing about the dispersion of values between two extreme values.
  • #179 S.D. gives us idea of the spread of dispersion . • Larger the standard deviation, greater the dispersion of values about the mean
  • #199 Unpaired t-test: applied on unpaired data of independent observations made on individuals of two different or separate groups or samples drawn from two populations • Paired t-test: applied to paired data of independent observations from one sample only