Session 6 - Sampling Technique

8/2/2019 Session 6 - Sampling Technique

1/23

Click to edit Master subtitle style

11

Session

6Sampling techniques


2/23

Research Proposal Assign.given in last class

Executive SummaryBackground Problem Definition/Objectives of the

ResearchApproach to the Problem (Theoretical

background with references, RQs andHypotheses)

Research Design Fieldwork/Data CollectionData AnalysisReporting (Contents, etc) PERT/CPM chartAppendices (Relevant textbook material,

To be submitted & presented in thenext class

22


3/23

Sample vs. Census

Cond i t io n s F a v o r i n g t h e U s e o fT ype o f S t ud y S am p l e Cen su s

1 . Bud ge t Sma l l L a r g e2 . Tim e av a i l ab l e Sho r t L ong3 . Po pu l a t i on s i z e L a r g e Sma l l4 . Va r i ance i n t he cha rac t e r i s t ic Sma l l L a r g e5 . Co s t o f s am p l i ng e r r o r s L o w H i g h6 . Cos t o f nonsam p l i ng e r r o r s H i g h L ow7 . Na t u r e o f mea su r em en t Des t ruc t i v e Nondes t ruc t i v e8 . A t t en t i on t o i nd i v i dua l ca ses Y e s N o 33


4/23

The Sampling Design Process

Define the Population

Determine the Sampling Frame

Select Sampling Technique(s)

Determine the Sample Size

Execute the Sampling Process

44


5/23

Define the Target Population

The target population is the collection of elements

or objects that possess the information sought by the

researcher and about which inferences are to be

made. The target population should be defined in

terms of elements, sampling units, extent, and time.

An element is the object about which or from

which the information is desired, e.g., the

respondent.A sampling unit is an element, or a unit

containing the element, that is available for

selection at some stage of the sampling process.

55


6/23

Classification of SamplingTechniques

Sampling Techniques

NonprobabilitySampling Techniques ProbabilitySampling

Techniques

Convenience

Sampling

Judgmental

Sampling

Quota

Sampling

Snowball

Sampling

Systemat

icSampling

Stratifie

dSampli

Cluster

Sampling

OtherSampling

Techniques

Simple

Random 66


7/23

Convenience Sampling

Convenience sampling attempts to obtain asample of convenient elements. Often, respondentsare selected because they happen to be in the right

place at the right time.

use of students, and members of socialorganizations

mall intercept interviews without qualifying therespondents

department stores using charge account lists

people on the street interviews

77


8/23

Judgmental Sampling

Judgmental sampling is a form of conveniencesampling in which the population elements areselected based on the judgment of the researcher.

test markets

purchase engineers selected in industrialmarketing research

bellwether precincts selected in voting behaviorresearch

expert witnesses used in court

88


9/23

Quota Sampling

Quota sampling may be viewed as two-stage restrictedjudgmental sampling.

The first stage consists of developing control categories, orquotas, of population elements.

In the second stage, sample elements are selected based on

convenience or judgment.

Population Samplecomposition composition

Control

Characteristic Percentage Percentage NumberSexMale 48 48 480Female 52 52 520

____ ____ ____ 100 100 1000

99


10/23

Snowball Sampling

In snowball sampling, an initial group ofrespondents is selected, usually at random.

After being interviewed, these respondents areasked to identify others who belong to the targetpopulation of interest.

Subsequent respondents are selected based on

the referrals.

1010


11/23

Simple Random Sampling - SRS

Each element in the population has a known andequal probability of selection.

Each possible sample of a given size (n) has aknown and equal probability of being the sampleactually selected.

This implies that every element is selectedindependently of every other element.

1111


12/23

Systematic Sampling

The sample is chosen by selecting a random starting pointand then picking every ith element in succession from thesampling frame.

The sampling interval, i, is determined by dividing thepopulation size N by the sample size n and rounding to the

nearest integer.When the ordering of the elements is related to the

characteristic of interest, systematic sampling increases therepresentativeness of the sample.

If the ordering of the elements produces a cyclical pattern,

systematic sampling may decrease the representativenessof the sample.

For example, there are 100,000 elements in the populationand a sample of 1,000 is desired. In this case the samplinginterval, i, is 100. A random number between 1 and 100 is

selected. If, for example, this number is 23, the sampleconsists of elements 23 123 223 323 423 523 and so on.

1212


13/23

Stratified Sampling

A two-step process in which the population ispartitioned into subpopulations, or strata.

The strata should be mutually exclusive and

collectively exhaustive in that every populationelement should be assigned to one and only onestratum and no population elements should beomitted.

Next, elements are selected from each stratum bya random procedure, usually SRS.

A major objective of stratified sampling is toincrease precision without increasing cost.

1313


14/23

Cluster Sampling

The target population is first divided into mutually exclusiveand collectively exhaustive subpopulations, or clusters.

Then a random sample of clusters is selected, based on aprobability sampling technique such as SRS.

For each selected cluster, either all the elements areincluded in the sample (one-stage) or a sample of elementsis drawn probabilistically (two-stage).

Elements within a cluster should be as heterogeneous aspossible, but clusters themselves should be ashomogeneous as possible. Ideally, each cluster should be asmall-scale representation of the population.

In probability proportionate to sizesampling, theclusters are sampled with probability proportional to size. Inthe second stage, the probability of selecting a sampling

unit in a selected cluster varies inversely with the size of the1414


15/23

Types of Cluster Sampling

Cluster Sampling

One-StageSampling

MultistageSampling

Two-StageSampling

Simple ClusterSampling

ProbabilityProportionate

to Size Sampling

1515


16/23

Techniq

ue

Strengt

hs

Weaknes

sesNonprobability

SamplingConvenience

sampling

Least expensive,

leasttime-consuming,

mostconvenie

nt

Selection bias, sample

notrepresentative, not recommended

fordescriptive or causal

researchJudgmental

sampling

Low cost,

convenient,not time-

consuming

Does not allow

generalization,subjecti

veQuota

sampling

Sample can be

controlledfor certaincharacteristics

Selection bias, no assurance

ofrepresentativenessSnowball

sampling

Can estimate

rarecharacteristi

cs

Time-

consuming

Probability

samplingSimple random

sampling(S

RS)

Easily

understood,resul

ts

projecta

ble

Difficult to construct

samplingframe,

expensive,

lower

precision,no assurance

of

representativen

ess.

Systematic

sampling

Can

increaserepresentativen

ess,easier to implement

thanSRS, sampling frame

notnecessa

ry

Can

decrease

representativen

ess

Stratified

sampling

Include all

importantsubpopulatio

ns,precisi

on

Difficult to select

relevantstratification variables, not

feasible tostratify on many variables,

expensiveCluster

sampling

Easy to implement,

costeffecti

ve

Imprecise, difficult to compute

andinterpret

results

Strengths and Weaknesses ofBasic Sampling Techniques

1616


17/23

Procedures for DrawingProbability Samples

SimpleRandomSampling

1. Select a suitable sampling frame

2. Each element is assigned a number from 1 to N(pop. size)

3. Generate n (sample size) different randomnumbers

between 1 and N

4. The numbers generated denote the elements thatshould be included in the sample

1717


18/23

Procedures for Drawing

Probability Samples

SystematicSampling

1. Select a suitable sampling frame

2. Each element is assigned a number from 1 to N (pop.size)

3. Determine the sampling interval i:i=N/n. If i is afraction,

round to the nearest integer

4. Select a random number, r, between 1 and i, asexplained in

simple random sampling

5. The elements with the following numbers will comprise

thesystematic random sample: r, r+i,r+2i,r+3i,r+4i,...,r+1818


19/23

1. Select a suitable frame

2. Select the stratification variable(s) and the number ofstrata, H

3. Divide the entire population into H strata. Based on theclassification variable, each element of the population is

assignedto one of the H strata

4. In each stratum, number the elements from 1 to Nh (the

pop.size of stratum h)

5. Determine the sample size of each stratum, nh, based onproportionate or disproportionate stratified sampling,

where


Probability Samples

nh =

nh=1

H

StratifiedSampling

1919


20/23


Probability Samples

ClusterSampling

1. Assign a number from 1 to N to each element in thepopulation2. Divide the population into C clusters of which c will beincluded in

the sample3. Calculate the sampling interval i, i=N/c (round to nearestinteger)4. Select a random number r between 1 and i, as explained insimple

random sampling

5. Identify elements with the following numbers:r,r+i,r+2i,... r+(c-1)i

6. Select the clusters that contain the identified elements7. Select sampling units within each selected cluster based onSRS

or systematic sampling8. Remove clusters exceeding sampling interval i. Calculate2020


21/23

Procedures for DrawingProbability Samples

Repeat the process until each of the remainingclusters has a population less than the

sampling interval. If b clusters have beenselected with certainty, select the remainingc-b clusters according to steps 1 through 7.The fraction of units to be sampled withcertainty is the overall sampling fraction = n/N.Thus, for clusters selected with certainty, we

would select ns=(n/N)(N1+N2+...+Nb) units. Theunits selected from clusters selected underPPS sampling will therefore be n*=n- ns.

ClusterSampling

2121


22/23

Choosing Nonprobability vs.Probability Sampling

C on d i t io n s F a v o r i n g t h e U s e o fFa c t o r s Nonp robab i l i t ys a m p l i n g P r obab i l i t ys a m p l i n gN a tu r e o f r e s ea r ch Exp l o r a t o r y Conc l u s i v e

R e l a t iv e m a gn i t u de o f s a m p l i n ga n d n on s a m p l in g e r r o rs N o n s a m p l i n ge r r o r s a r el a r ge rS a m p l i n ge r ro r s a rel a r ge r

Va r i a b i l it y i n t h e pop u l a t i on H o m o g e n e o u s( l o w ) He t e r oge n e ou s( h i g h )S t a t i s ti c a l c o n s i de r a t i on s Un f a vo r ab l e Fa vo r ab l e

Ope r a t i ona l con s i de r a t i on s Favo r ab l e Un f a vo r ab l e2222


23/23

Click to edit Master subtitle style

2323

Next

Assignment Data collection process and field work

Quiz from sampling

Session 6 - Sampling Technique

Documents