Sampling by dr najeeb memon

By: By:

Assist: Prof:Assist: Prof:Faculty of Community Medicine & Public Health Faculty of Community Medicine & Public Health SciencesSciencesLiaquat University of Medical & Health Sciences Liaquat University of Medical & Health Sciences (LUMHS)(LUMHS) Jamshoro, Sind, Jamshoro, Sind, PakistanPakistan e maile mail [email protected]@gmail.com

LIAQUAT

MEDICAL

UNIVERSITY

POPULATIONPOPULATION The whole group of the individuals on which the results of the study are to be generalized is known as Population. A

SAMPLE small group of individuals chosen for

the study is known as Sample.

The entire group of people of interest from whom the researcher needs to obtain information.

The selection of a subset of the population

Sampling FrameSampling FrameListing of all the members of the

universe from which the sample is to be taken , is known as Sampling Frame.

Sampling frame should be carefully developed as it affects the results drawn.

Listing of population from which a sample is chosen

WHY SAMPLING IS WHY SAMPLING IS NECESSARY?NECESSARY?

Convenient. Economic. Time saving. Less resources are required. Easy to interpret the data.

TYPES OF SAMPLINGTYPES OF SAMPLING

• A. Probability Sampling MethodsProbability Sampling Methods

• B. Non Probability Sampling MethodsB. Non Probability Sampling Methods

14-11

SAMPLES TECHNIQUESSAMPLES TECHNIQUESA. A. Probability Sampling MethodsProbability Sampling Methods

Simple RandomSimple RandomSimple RandomSimple Random

systemic systemic samplingsamplingsystemic systemic samplingsampling

StratifiedStratifiedStratifiedStratified

ClusterClusterClusterCluster

MultistageMultistageMultistageMultistage

14-12

B. Non probability B. Non probability Sampling Methods Sampling Methods

ConvenienceConvenienceConvenienceConvenience

JudgmentJudgmentJudgmentJudgment

QuotaQuotaQuotaQuota

SnowballSnowballSnowballSnowball

Each element in the population will have an equal chance of being included in the sample.

1 - 13

1. Simple Random 1. Simple Random samplingsampling

1. Simple Random 1. Simple Random samplingsampling

No: is given to each of units (Persons/ houses)Table of random Nos: is usedSamples selected haphazardly (Each has equal chance of being selected)

N = 100 population size, n = 8 sample size

OR Lottery Method

E.g:- In Electro roll / Census

Simple random sampling

Selecting unit/ person Selecting unit/ person after a regular after a regular intervalinterval

1 - 15

2. 2. systemic samplingsystemic sampling2. 2. systemic samplingsystemic sampling

Systematic sampling

3. Stratified3. Stratified3. Stratified3. Stratified

It involves division of population in to smaller groups (homogenous subgroups)

known as “Strata”

•Then Simple random sampling OR systematic sampling is applied with each stratum.

Example 2 Population is divided on the basis of characteristic of interest in the population E.g. male & female may have different consumption patterns.

1 - 18

Here we select a simple random sample of groups such as a certain number of city blocks & then select a person each from each block.

This technique is more economical than the random selection of persons through out the city.

4. Cluster4. Cluster4. Cluster4. Cluster

Cluster samplingCluster sampling

Section 4

Section 5

Section 3

Section 2Section 1

• Sampling at different stages/ Levels• 1. National level• 2. Provincial level• 3. District level

5. Multistage5. Multistage5. Multistage5. Multistage

A sample selected in stages, beginning with the most unspecific level (such as regions) and ending with the most specific (such as houses on selected city blocks).

Non probability MethodsNon probability Methods

NON PROBABILITY NON PROBABILITY SAMPLINGSAMPLING

• Convenient

• Economic

BUT

RESULTS CAN NOT BE GENERALIZED

THEREFORE

Some probability factor is needed to be imposed to ensure a degree of representation in the sample.

A convenience sample is a sample where the patients are selected, in part or in whole, at the convenience of the researcher.

Example: Male on street interviews Teacher uses students

1. Convenience /Accidental/Incidental 1. Convenience /Accidental/Incidental samplingsampling

1. Convenience /Accidental/Incidental 1. Convenience /Accidental/Incidental samplingsampling

Involves the use of the most convenient & readily available subjects for sample.

The researcher chooses the sample based on who they think would be appropriate for the study.

2. Judgment /Purposive2. Judgment /Purposive2. Judgment /Purposive2. Judgment /Purposive

3. Quota3. Quota3. Quota3. Quota

if you are a researcher conducting a national quota sample, you might need to know what proportion of the population is male(40) and what proportion is female (60) as well as what proportions of each gender fall into different age categories, race or ethnic categories, educational categories, etc.

Researcher selects people according to some fixed quota.OR Keep going until the sample size is reached

Male 40

Female 60

Total (Fixed quota) 100

Researcher collects data on the few members of the target population he or she can locate, then asks those individuals to provide information needed to locate other members of that population whom they know.

4. Snowball4. Snowball4. Snowball4. Snowball

Get sampled people to nominate others

Sampling ErrorsSampling Errors A. Size: sample size should be large as possible

depends upon feasibility (time, person, importance of data)

B. subject variation: Sometimes observation may be changed on

different times (B.P at different times of a day)

C. Observer Variation: When 2 or more persons observe same data

(No same value) E.g:- Taking Blood Pressure reading

D. Technical Fault: By Instrument

E. Incomplete Coverage: If 10 out of 100 are non cooperative (i,e 90

or 10 Non co operative)

THANKYOU