sampling method

SAMPLING METHODSSAMPLING METHODS

Dr Bindu John PulparampilDr Bindu John Pulparampil

AMO, VSSCAMO, VSSC

Govt Of IndiaGovt Of India

What is Sampling ?What is Sampling ?

• Procedure by which some members Procedure by which some members of a population are selected as of a population are selected as representative of the entire representative of the entire populationpopulation

• The sub-group thus selected to The sub-group thus selected to represent the whole population is represent the whole population is known as SAMPLEknown as SAMPLE

Methods Of SamplingMethods Of Sampling

• Several methods are used to Several methods are used to ascertain a particular aspect of the ascertain a particular aspect of the population,through an unbiased population,through an unbiased sample drawn from the populationsample drawn from the population

• Sampling is divided in two categoriesSampling is divided in two categories

• 1. Probability Sampling1. Probability Sampling

• 2. Non-probability Sampling 2. Non-probability Sampling

Probability samplingProbability sampling

• It is any method of sampling that It is any method of sampling that utilizes some form of utilizes some form of random random selectionselection

• The procedure should assure that the The procedure should assure that the different units in the population different units in the population have equal probabilities of being have equal probabilities of being chosen.chosen.

Non probability samplingNon probability sampling

• It does not involve It does not involve randomrandom selection selection

• May or may not represent the May or may not represent the population well population well

• Used when researcher lacks a Used when researcher lacks a sampling frame for the populationsampling frame for the population

Probability samplingProbability sampling

• Includes: Includes:

• Simple Random MethodSimple Random Method

• Systematic Sampling Systematic Sampling

• Stratified SamplingStratified Sampling

• Cluster SamplingCluster Sampling

• Multistage SamplingMultistage Sampling

Nonprobability SamplingNonprobability Sampling

• Includes :Includes :

• Accidental SamplingAccidental Sampling

• Voluntary SamplingVoluntary Sampling

• Purposive SamplingPurposive Sampling

• Quota SamplingQuota Sampling

Simple Random SamplingSimple Random Sampling

• A sample selected such that each A sample selected such that each possible sample combination has possible sample combination has equal probability of being chosen.equal probability of being chosen.

• Also called Unrestricted random Also called Unrestricted random samplingsampling

Simple random sampling Simple random sampling without replacementwithout replacement::

• In this method the population In this method the population elements can enter the sample only elements can enter the sample only once once

• The units once selected is not The units once selected is not returned to the population before the returned to the population before the next drawnext draw

Simple random sampling with Simple random sampling with replacement replacement

The population units may enter the The population units may enter the samplesample

more than oncemore than once

Methods of selection of a Methods of selection of a simple random sampling: simple random sampling:

• Lottery Method Lottery Method

• Table of Random numbers Table of Random numbers

• Random number selections using Random number selections using calculators or computerscalculators or computers

Systematic Random Systematic Random SamplingSampling• Also called Quasi-random sampling Also called Quasi-random sampling • Divide the population size by the Divide the population size by the

sample size, to get sampling fractionsample size, to get sampling fraction• Select a random number b/w 1 and Select a random number b/w 1 and

sampling fraction, which is the first sampling fraction, which is the first sampling unitsampling unit

• Systematically select the remaining Systematically select the remaining sample units, by adding sampling sample units, by adding sampling factionfaction

Stratified Random SamplingStratified Random Sampling

• Stratification means division into Stratification means division into groups.groups.

• In this method the population is divided In this method the population is divided into a number of subgroups or stratainto a number of subgroups or strata

• From each stratum a simple random From each stratum a simple random sample is selected and combined sample is selected and combined together to form the required sample together to form the required sample from the populationfrom the population

Multi- Stage SamplingMulti- Stage Sampling

• Used in large scale investigationsUsed in large scale investigations

• First stage- preparation of large sized First stage- preparation of large sized sampling units sampling units

• Randomly selecting a certain numberRandomly selecting a certain number

• Second stage- Another list prepared Second stage- Another list prepared from themfrom them

• Sub-samples drawn by random Sub-samples drawn by random samplingsampling

Multi –Phase SamplingMulti –Phase Sampling

• Used to obtain supplementary Used to obtain supplementary informationinformation

• Certain items of information Certain items of information collected from all units of samplecollected from all units of sample

• Other items collected from only some Other items collected from only some of sampling unitsof sampling units

Cluster SamplingCluster Sampling

• Each sampling unit is a collection or Each sampling unit is a collection or cluster of elementscluster of elements

• Used when units of population are Used when units of population are natural groups or clusters like wards, natural groups or clusters like wards, villages etcvillages etc

• The group is taken as a sampling unitThe group is taken as a sampling unit

Non- Probability SamplingNon- Probability Sampling

Accidental SamplingAccidental Sampling

• The "person on the street" interviews The "person on the street" interviews conducted frequently by television conducted frequently by television news programsnews programs

• Sampling those most convenientSampling those most convenient

• Gets a quick reading of public opinion Gets a quick reading of public opinion

• Also called Haphazard or Convenience Also called Haphazard or Convenience Sampling Sampling

Voluntary samplingVoluntary sampling

• The sample is self selectedThe sample is self selected

• Sample consists of people who chose Sample consists of people who chose themselves by responding to a themselves by responding to a general appeal. general appeal.

• They often over represent people They often over represent people with strong opinions, most often with strong opinions, most often negative opinions.negative opinions.

Purposive Sampling Purposive Sampling

• Sampling with a Sampling with a purposepurpose in mind in mind

• Handpicking supposedly typical or Handpicking supposedly typical or interesting casesinteresting cases

• Reaches a targeted sample quickly Reaches a targeted sample quickly

• Also known as Judgemental samplingAlso known as Judgemental sampling

Types of Purposive Types of Purposive SamplingSampling• Sampling for specific types of people Sampling for specific types of people

- modal instance, expert, or quota - modal instance, expert, or quota sampling. sampling.

• Sampling for diversity - heterogeneity Sampling for diversity - heterogeneity sampling. sampling.

• Snowball sampling - capitalize on informal Snowball sampling - capitalize on informal social networks to identify specific social networks to identify specific respondents who are hard to locate respondents who are hard to locate otherwise otherwise

Modal instance samplingModal instance sampling

• Sampling the most frequent case, or Sampling the most frequent case, or the "typical" case the "typical" case

• Is only sensible for informal sampling Is only sensible for informal sampling contexts. contexts.

Expert samplingExpert sampling

• It involves the assembling of a It involves the assembling of a sample of persons with known or sample of persons with known or demonstrable experience and demonstrable experience and expertise in some area expertise in some area

Quota samplingQuota sampling

• The population is first segmented into The population is first segmented into mutually exclusive sub-groups.mutually exclusive sub-groups.

• People are selected nonrandomly People are selected nonrandomly according to some fixed quota according to some fixed quota

• Judgement is used to select the subjects or Judgement is used to select the subjects or units from each segment based on a units from each segment based on a specified proportion specified proportion

• Convienience sampling within population Convienience sampling within population groupsgroups

Quota samplingQuota sampling

• ProportionalProportional and and non proportionalnon proportional• Proportional quota sampling :It is Proportional quota sampling :It is

representing the major representing the major characteristics of the population by characteristics of the population by sampling a proportional amount of sampling a proportional amount of eacheach

• Nonproportional quota sampling : Nonproportional quota sampling : The minimum number of sampled The minimum number of sampled units in each category is specifiedunits in each category is specified

Heterogeneity SamplingHeterogeneity Sampling

• When all opinions or views are to be When all opinions or views are to be included and are not concerned included and are not concerned about representing these views about representing these views proportionatelyproportionately

Snowball samplingSnowball sampling

• It begins by identifying someone who It begins by identifying someone who meets the criteria for inclusion in the meets the criteria for inclusion in the study. study.

• They are asked to recommend They are asked to recommend others who they may know who also others who they may know who also meet the criteria meet the criteria

Other Kinds Of SamplingOther Kinds Of Sampling

• Event Sampling : Using routine or Event Sampling : Using routine or special events as the basis for special events as the basis for samplingsampling

• Time Sampling : Recognising that Time Sampling : Recognising that different parts of the day, week or different parts of the day, week or year may be significantyear may be significant

In A Nut ShellIn A Nut Shell

• Probability SamplingProbability Sampling

- Simple Random – Selection at Random- Simple Random – Selection at Random

- Systematic – Selecting every nth caseSystematic – Selecting every nth case

- Stratified – Sampling w/n groups of PopulnStratified – Sampling w/n groups of Populn

- Cluster – Surveying whole clusters of P/nCluster – Surveying whole clusters of P/n

- Multistage – Sub samples from large smplMultistage – Sub samples from large smpl

• Non- Probability SamplingNon- Probability Sampling

- Accidental – Sampling those most Accidental – Sampling those most convntconvnt

- Voluntary – Sample is self selectedVoluntary – Sample is self selected

- Purposive – Handpicking typical casesPurposive – Handpicking typical cases

- Quota – Sampling w/n groups of PplnQuota – Sampling w/n groups of Ppln

- Snowball – building sample thru Snowball – building sample thru informntsinformnts

THANK YOUTHANK YOU