Dr Zia-Ul-Ain Sabiha. At the end of this session the students will be able to Define Statistics ...

Preview:

Citation preview

Introduction to Biostatistics

Dr Zia-Ul-Ain Sabiha

CHS deptt 2

Objectives of this lecture

At the end of this session the students will be able to

Define Statistics Differentiate between Descriptive

Statistics and Inferential Statistics Define Biostatistics Discuss the Uses of Biostatistics

9/6/2015

CHS deptt 3

Cont’d

Define Data Sample and Population Variables Measurement variables Types of Data Exercises to summarize the lecture.

9/6/2015

CHS deptt 4

STATISTICS

Statistics is science of conducting studies to collect ,organize, summarize, analyze, and draw conclusions from the data.

9/6/2015

CHS deptt 5

Concern of Statistics

A subject that deals with the collection , compilation , presentation , analysis and presentation of data.

Drawing inferences about a body of data when only a part of the data is observed.

Scientific study of numerical data based on natural phenomenon

9/6/2015

CHS deptt 6

Types of statistics

9/6/2015

CHS deptt 7

Types of statistics

Descriptive Statistics Consists of the collection , organization ,

summarization, and presentation of data.

Inferential statistics consists of generalizing from samples to

populations ,performing estimations and hypothesis tests, determining relationships among variables and making predictions.

It uses probability i,e., the chance of event occuring

9/6/2015

CHS deptt 8

HISTORICAL NOTE

The origin of descriptive Statistics can be traced to data collection methods used in censuses taken by the Babylonians and Egyptians between 4500 and 3000 B.C.

In addition the Roman Emperor Augustus (27 B.C-A.D. 17) conducted surveys on births and deaths of the citizens of the empire, as well as the number of livestock each owned and the crops each citizen harvested yearly.

9/6/2015

CHS deptt 9

Historical Note

Inferential Statistics originated in the 1600s, when John Graunt published his book on population growth , Natural and Political Observations Made upon the Bills of Mortality.

About the same time ,another mathematician/astronomer , Edmund Hally, published the first complete mortality tables.( insurance companies use mortality tables to determine life insurance rates).

9/6/2015

CHS deptt 10

Biostatistics

Application of Statistical methods to the solution of biological problems

9/6/2015

CHS deptt 11

Uses of Biostatistics

In Epidemiology In demography Morbidity and mortality rates and ratios. Collection and registration of vital events.

(Births ,Deaths , Marriages and divorces) Sampling for different statistical procedures. To know the frequency of different diseases

and biological problems. For interpretation of data. To know about association and causation of

diseases.9/6/2015

CHS deptt 129/6/2015

CHS deptt 13

Data

Record of observations Facts and figures Any piece of information

InformationWhen data is processed and made meaningful

9/6/2015

CHS deptt 14

Data are numbers which can be measured or can be obtained by counting.  Biostatistics is concerned with the interpretation of the data and the communication of information about the data.

9/6/2015

CHS deptt 15

Sources of data

Data are obtained from Analysis of records Surveys Counting Experiments Reports

9/6/2015

CHS deptt 16

Variable

A characteristics ,object and property that assumes different numerical value for each possible outcome/individual/element of the population or sample is called a variable.

The actual property measured on the individual selected for sample.

E.g. Height ,weight ,temprature,age,smoking,

9/6/2015

CHS deptt 17

Random variables

 A random variable is one that cannot be predicted in advance because it arises by chance.  Observations or measurements are used to obtain the value of a random variable.

Random variables may be discrete or continuous.

        Discrete random variable

A discrete random variable has gaps or interruptions in the values that it can have.  The values may be whole numbers or have spaces between them.

        Continuous random variable

A continuous random variable does not have gaps in the values it can assume.  Its properties are like the real numbers.

9/6/2015

CHS deptt 18

Type of variables

9/6/2015

CHS deptt 19

Types of Variables

9/6/2015

CHS deptt 20

Classification of variable

Independent and dependent Independent variables are presumed

causes and dependent variables are presumed effects.

9/6/2015

CHS deptt 219/6/2015

CHS deptt 22

Population

The whole set of things about which we want to know.

In biostatistics population can be human beings , ECG machines , Paracetamol tablets.

A population is the collection or set of all of the values that a variable may have.  A sample is a part of a population.

9/6/2015

CHS deptt 23

Sample

A part or subset of population for actual study. OR

A collection of individual observations selected by a specific procedure from a population.

9/6/2015

CHS deptt 24

Types of variables

Measurement variable Continuous variables Discontinuous variables or discrete

variable Ranked variables Categorical variable

9/6/2015

CHS deptt 25

Measurement variables

Continuous variables Which at least theoretically can assume

an infinite number of values between any two points . e. g length ,period of time ,height , weight , age ,

Discrete, Discontinuous variables That has only certain fixed numerical

values with no intermediate values possible in between. e.g. number of offsprings , no. of teeth, no. of glands.

9/6/2015

CHS deptt 26

Ranked variables

Which cannot be measured but ranked or ordered .e.g. rank order of pupa emergence or seed germination.

9/6/2015

CHS deptt 27

Attributes variables

The characteristics that are qualitative in character and hence cannot be expressed numerically( or quantitatively) are called descriptive characteristics or attributes. The sex of a newly born baby. Eye color of a girl. The language of a Arabian visitor. The style of a speaker

9/6/2015

CHS deptt 28

Types of Data

Data consists of variables. There are four scales of

measurement Nominal(category) Ordinal(category) Interval(quantity ,continuous ) Ratio(quantity , continuous)

9/6/2015

CHS deptt 29

Scale Characteristic question Example

Nominal Is A different than B? Marital status Eye color Gender Religious affiliations Race

ordinal Is A bigger than B? Stage of disease Severity of pain Level of satisfaction

Interval By how many units do A and B differs?

Temperature SAT score

Ratio How many times bigger than B is A?

Distance Length Time until death Weight

9/6/2015

CHS deptt 30

Nominal Scale

Classifies persons or things based on the characteristic being assessed

No information is given on quantity or amount

A variable without an intrinsic order. Examples Male or female Nationality (American , Mexican ,

Pakistani) Favorite pet( dog , cat, fish, snake)

9/6/2015

CHS deptt 31

Ordinal Scale

Classifies persons or things based on the characteristic being assessed

Can be placed in meaningful order, Indicates “more than” or “less than” Does not indicate how much more or

how much less than Example: Rating a student’s

performance as ‘good’, ‘fair’, ‘poor’

9/6/2015

CHS deptt 32

Interval Scale

Classifies persons or things based on the characteristic being assessed

Indicates “more than” or “less than ” and the magnitude of the observation

There is no true zero or meaningful zero.

Examples Temperature Year of birth Date of diagnosis

9/6/2015

CHS deptt 33

Ratio Scale

Classifies persons or things based on the characteristic being assessed

Indicates “more than” or “less than” and the magnitude of the observation

Zero point is indicated True ratios exist when the same variable is

measured on the different members f the population.

Examples: Height Weight Age 9/6/2015

CHS deptt 34

Identify what type of variable it is.

Date of diagnosis Town of residence Age (years) Sex

9/6/2015

CHS deptt 35

Exercise

Date of diagnosis: Interval Town of residence: Nominal Age (years): Ratio Sex : Nominal

9/6/2015

CHS deptt 36

Exercise

Name the scale of measurement for each variable below:

Year of birth: Marital status of a women: Identification number of study

participants: Class rank: Length of infants at ANC clinic:

9/6/2015

CHS deptt 37

Exercise

Year of birth: Interval Marital status of a women: Nominal Identification number : Nominal Class rank: Ordinal Length/Height of infants at ANC

clinic: Ratio

9/6/2015

CHS deptt 38

Summary

Identify whether the following data is discrete or continuous

Distance from primary health center to reference lab:

Number of times a child under 5 has experienced fever in the last month:

Number of fatal accidents on a road over the past year:

Weight gained or lost by a 9 month old in the past 3 months:

9/6/2015

CHS deptt 39

Exercise

Distance from primary health center to reference lab: Continuous

Number of times a child under 5 has experienced fever in the last month: Discrete

Number of fatal accidents on a road over the past year: Discrete

Weight gained or lost by a 9 month old in the past 3 months: Continuous

9/6/2015

CHS deptt 409/6/2015