Chapter Eleven Sampling: Design and Procedures Copyright © 2010 Pearson Education, Inc. 11-1.
-
Upload
scarlett-cook -
Category
Documents
-
view
220 -
download
0
Transcript of Chapter Eleven Sampling: Design and Procedures Copyright © 2010 Pearson Education, Inc. 11-1.
Chapter Eleven
Sampling: Design and Procedures
Copyright © 2010 Pearson Education, Inc. 11-1
Copyright © 2010 Pearson Education, Inc. 11-2
1. Chapter Outline
1) Overview
2) The Sampling Design Process
3) A Classification of Sampling Techniques
4) Nonprobability Sampling
5) Probability Sampling
6) Choosing Nonprobability Versus Probability Sampling
Copyright © 2010 Pearson Education, Inc. 11-3
2. The Sampling Design Process
A. Define the Population
B. Determine the Sampling Frame
C. Select Sampling Technique(s)
D. Determine the Sample Size
E. Execute the Sampling Process
Copyright © 2010 Pearson Education, Inc. 11-4
2. The Sampling Design Process: Define the Target Population
A. Define the Target PopulationThe target population is the collection of
elements/objects/people 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:
• An element is the object about which or from which the information is desired• e.g., a person in the population.
• A sampling unit is an element that is available for selection at some stage of the sampling process. • E.g., a respondent who takes your survey
• Extent refers to the geographical boundaries.• Time is the time period under consideration.
Copyright © 2010 Pearson Education, Inc. 11-5
Important factors in determining the sample size are:
• the nature of the research• Surveys need more people; qualitative
interviews need less
• the number of variables• More variables = more people
• the nature of the analysis• Certain methods require more people –
e.g. t-tests need more than simple averages.
• sample sizes used in similar studies
2. The Sampling Design Process: Define the Target Population
Copyright © 2010 Pearson Education, Inc. 11-6
2. Sample Sizes Used in Marketing Research Studies
Type of Study
Minimum Size Typical Range
Market potential research
500
1,000-2,500
Pricing research
200 300-500
Product tests
200 300-500
Test marketing studies
200 300-500
TV, radio, or print advertising (per commercial or ad tested)
150 200-300
Test-market audits
10 stores 10-20 stores
Focus groups
2 groups 6-15 groups
Copyright © 2010 Pearson Education, Inc. 11-7
3. Classification of Sampling Techniques
Sampling Techniques
NonprobabilitySampling
Techniques
ProbabilitySampling
Techniques
ConvenienceSampling
JudgmentalSampling
QuotaSampling
SnowballSampling
SystematicSampling
StratifiedSampling
ClusterSampling
Simple RandomSampling
Copyright © 2010 Pearson Education, Inc. 11-8
3. Classification of Sampling Techniques
• A probability sampling scheme is one in which every unit in the population has a chance (greater than zero) of being selected in the sample.
• Nonprobability sampling is any sampling method where some elements of the population have no chance of selection • these are sometimes referred to as 'out of
coverage'/'undercovered'.
Copyright © 2010 Pearson Education, Inc. 11-9
4. Nonprobability Sampling -Convenience Sampling
Nonprobability sampling techniques include:convenience, judgmental, quota, and snowball sampling
Convenience sampling attempts to obtain a sample of convenient elements. Often, respondents are selected because they happen to be in the right place at the right time. Examples: • Use of student respondents• Members of social organizations• “People on the street” interviews
Copyright © 2010 Pearson Education, Inc. 11-10
4. Nonprobability Sampling - Judgmental Sampling
Judgmental sampling is a form of convenience sampling in which the population elements are selected based on the judgment of the researcher.
Examples: • Test markets.
• e.g. Columbus, OH• Bellwether precincts (precincts that indicate
broader trends) selected in voting behavior research.
• Expert witnesses used in court.
Copyright © 2010 Pearson Education, Inc. 11-11
4. Nonprobability Sampling - Quota Sampling
Quota sampling may be viewed as two-stage restricted judgmental sampling. 1. The first stage consists of developing quotas of
population elements. 2. In the second stage, sample elements are selected
based on convenience or judgment.
Quota Population SampleVariable composition
composition319m. total 1000 total
Sex Percentage PercentageNumber
Male 48% 48% 480 Female 52% 52% 520
____ ____ ____100% 100% 1000
Copyright © 2010 Pearson Education, Inc. 11-12
4. Nonprobability Sampling - Snowball Sampling
In snowball sampling, an initial group of respondents is selected, usually at random.
• After being interviewed, these respondents are asked to identify others who belong to the target population of interest.
• Subsequent respondents are selected based on the referrals.
Copyright © 2010 Pearson Education, Inc. 11-13
5. Probability Sampling – Simple Random Sampling
Probability sampling techniques include:•Simple random, systematic, stratified, and cluster sampling
Simple Random Sample:•Each element in the population has a known and equal probability of selection. • Each possible sample of a given size (n) has a
known and equal probability of being the sample actually selected.
• This implies that every element is selected independently of every other element.
Copyright © 2010 Pearson Education, Inc. 11-14
5. Probability Sampling – Systematic Sampling
Systematic Sampling
•The sample is chosen by selecting a random starting point and then picking every ith (e.g. 5th, 10th) element in succession from the sampling frame.
•The sampling interval, i, is determined by dividing the population 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 (e.g. age), systematic sampling increases the representativeness of the sample.
Copyright © 2010 Pearson Education, Inc. 11-15
5. Probability Sampling – Systematic Sampling
For example: • There are 100,000 people in the population (N).
• Each person is put into order based on age.
• A sample (n) of 1,000 is desired. • In this case the sampling interval, i, is 100.
• (100,000/1,000) = 100
• A random number between 1 and 100 is selected.• If, for example, this number is 23, the sample consists of elements 23, 123, 223, 323, 423, 523, and so on.
Copyright © 2010 Pearson Education, Inc. 11-16
5. Probability Sampling – Stratified Sampling
Stratified Sampling:1.A two-step process in which the population is partitioned into subpopulations, or strata.
• Every person in the population should be assigned to one and only one stratum and no population elements should be omitted.
2.Next, elements are selected from each stratum by a random procedure, usually simple random sampling.
•A major objective of stratified sampling is to increase precision without increasing cost.
Copyright © 2010 Pearson Education, Inc. 11-17
5. Probability Sampling – Stratified Sampling
• The elements/people within a stratum (e.g. male) should be as homogeneous as possible.
• The elements/people across strata (e.g. male, female) should be as heterogeneous as possible.
• The stratification variables should also be closely related to the characteristic of interest.
Copyright © 2010 Pearson Education, Inc. 11-18
5. Probability Sampling – Stratified Sampling
• In proportionate stratified sampling, the size of the sample drawn from each stratum is proportionate to the relative size of that stratum in the total population.
• E.g. stratify by gender, pick 50 men and 50 women
• In disproportionate stratified sampling, the size of the sample from each stratum is proportionate to the relative size of that stratum and to the standard deviation of the distribution of the characteristic of interest among all the elements in that stratum.
• E.g. gender + employment status (see next page)
Copyright © 2010 Pearson Education, Inc. 11-19
5. Probability Sampling – Disproportionate Stratified Sampling
Disproportionate Stratified Sampling, example:Suppose that in a company there are the following staff:• female, full time: 90• female, part time: 18• male, full time: 9• male, part time: 63• Total: 180
We are asked to take a sample of 40 staff, stratified according to the above categories.
Find the total number of staff (180), calculate the percentage in each group, and calculate the number per group
• % female, full time = 90 / 180 = 50% = 20• % female, part time = 18 / 180 = 10% = 4• % male, full time = 9 / 180 = 5% = 2• % male, part time = 63 / 180 = 35% = 14
Copyright © 2010 Pearson Education, Inc. 11-20
5. Probability Sampling – Cluster Sampling
Cluster Sampling:
1.The target population is first divided into mutually exclusive and collectively exhaustive subpopulations, or clusters.
2.Then a random sample of clusters is selected, based on a probability sampling technique such as simple random sampling.
3.For each selected cluster, either all the elements are included in the sample (one-stage) or a sample of elements is drawn probabilistically (two-stage).
Copyright © 2010 Pearson Education, Inc. 11-21
5. Probability Sampling – Cluster Sampling
Note: In stratified sampling, a random sample is drawn from each of the strata, whereas in cluster sampling only the selected clusters are studied (all elements are used).
Copyright © 2010 Pearson Education, Inc. 11-22
Technique Strengths WeaknessesNonprobability Sampling Convenience sampling
Least expensive, leasttime-consuming, mostconvenient
Selection bias, sample notrepresentative, not recommended fordescriptive or causal research
Judgmental sampling Low cost, convenient,not time-consuming
Does not allow generalization,Subjective, selection bias
Quota sampling Sample can be controlledfor certain characteristics
Selection bias, no assurance ofrepresentativeness
Snowball sampling Can estimate rareCharacteristics, convenient
Selection bias, time-consuming
Probability Sampling Simple random sampling
Representative,results, projectable
Difficult to construct samplingframe, expensive, lower precision
Systematic sampling Can increaserepresentativeness,easier to implement thanSRS, sampling frame notnecessary
Can accidentally decrease representativeness
Stratified sampling Include all importantsubpopulations,representative
Difficult to select relevantstratification variables, not feasible tostratify on many variables, expensive
Cluster sampling Easy to implement, costeffective, more representative
Imprecise, difficult to compute andinterpret results
6. Choosing Nonprobability Vs. Probability Sampling
Copyright © 2010 Pearson Education, Inc. 11-23
6. Choosing Nonprobability Vs. Probability Sampling
Conditions Favoring the Use of
Factors
Nonprobability sampling
Probability sampling
Nature of research
Exploratory
Conclusive
Variability in the population
Homogeneous (low variability)
Heterogeneous (high variability)
Statistical considerations
Unfavorable
Favorable
Operational considerations Favorable Unfavorable
Copyright © 2010 Pearson Education, Inc. 11-24
Thanks!
Questions??