Professional Documents
Culture Documents
Sampling Approaches
Learning Objectives
1. Understand the key principles of sampling in business research.
1
Sampling
Population Sample
• All elements that share a • Relatively small subset of the
common set of characteristics population.
– People, students, firms, etc. – Must be representative
• Parameter • Statistic
• Census • Procedures:
– Probability
– Nonprobability
Sampling
Questions:
1. Should a sample or a census be used?
2. If a sample, then which sampling approach is best?
3. How large a sample is necessary?
2
The sampling process
3
2. Choosing the sampling frame
• Sampling frame
– A comprehensive list of the elements from which the sample
is drawn.
• Ideally: An accurate, complete listing of all the elements in
the population targeted by the research.
• But, it may…
– Not be up-to-date.
– Include elements that do not belong to the target population.
– Not include elements that do belong to the target population.
– Have been compiled from multiple lists and contain duplicate
elements as a result of the manner in which the list was
constructed.
7
4
3. Selecting the sampling method
10
5
Systematic sampling
• Randomly selecting an initial starting point on a list,
thereafter every nth element in the sampling frame is
selected.
• Procedure:
– Determine sample size.
– Calculate the sampling interval
• Sampling interval: the number of population elements between each
unit selected for the sample.
– Randomly select a number of the sampling interval as a
starting point, e.g., n.
– Select the elements nth from the population.
11
Stratified sampling
• Partition the sampling frame into strata
– Strata: relatively homogeneous subgroups that are distinct
and nonoverlapping.
– On the basis of some predetermined criteria
• Determine:
– The total sample size.
– Sample size for each of individual strata.
• The stratified sample is the composite of the samples taken
from the strata.
12
6
Stratified sampling
• Proportionately stratified sampling:
– The number of elements chosen from each stratum is
proportionate to the size of a particular stratum relative to the
overall sample size.
• Disproportionately stratified sampling: two approaches
1. Choosing the elements from each stratum according to its
relative importance.
• Importance: based on practical consideration.
2. Elements from each stratum are selected based on the relative
variability of the elements
• Based on the variability of the data within each stratum.
13
Cluster sampling
• Clusters:
– Heterogeneous groups made up the target population.
– The clusters to be sampled would be randomly selected.
• Examples:
– Geographic areas
– Ethnic groups
– Companies
– Households
14
7
Cluster sampling: Procedure
1. Define the cluster characteristics.
– The clusters are unambiguously identified in the target population.
– The total number of clusters will be known ahead of time.
2. Decide on how many clusters to sample.
3. Choose the cluster(s) in a random manner.
4. Obtain a sampling frame for the chosen clusters.
5. Decide whether to conduct a census on the chosen cluster(s) or
whether to take a probability sample from the cluster(s).
6. If a probability sample is desired, determine the total sample size.
– If more than one cluster will be used, then the sample size should be
allocated appropriately; generally done on a proportionate sampling basis.
15
1 2 3 4 5 6
16
8
Convenience sampling
• Sample elements
– Most readily available to participate in the study
– Can provide the information required.
• Wed and social media:
– River sampling: Placing survey invitations on a website.
– Web scraping: Harvesting user-generated data from sites
where social media–engaged individuals have placed their
opinions or stimulated dialogue.
17
Judgement sampling
• Select elements in the sample for a specific purpose.
– Aka purposive sample.
– A form of convenience sampling: the researcher’s judgment
is used to select the sample elements.
18
9
Quota sampling
• Similar to stratified random sampling.
• Different: the selection of elements is done on a
convenience basis
• Procedure:
– Define the target population.
– Determine the total sample size.
– Set a quota for the sample elements from each stratum.
• Specify the characteristics of the elements to be selected.
• But leave the actual choice of elements to the discretion of the person
collecting the information.
19
20
10
Snowball/referral sampling
• The researcher then uses the initial respondents to help
identify the other respondents in the target population.
21
22
11
4. Determining the sample size
• Sampling from a large population
– Using statistical formulas:
• DC (degree of confidence): the number of standard errors for the degree
of confidence specified for the research results.
• DP (desired precision): the acceptable difference between the sample
estimate and the population value.
• TV (true variability): the standard deviation of the population.
𝑫𝑪 × 𝑻𝑽
𝑆𝑎𝑚𝑝𝑙𝑒 𝑆𝑖𝑧𝑒 𝑺𝑺 =
𝑫𝑷
• The calculated sample size does not necessarily ensure that the sample
is representative of the target population.
23
𝑫𝑪 × 𝑻𝑽 𝑵
𝑆𝑎𝑚𝑝𝑙𝑒 𝑆𝑖𝑧𝑒 𝑺𝑺 = ×
𝑫𝑷 𝑵+ 𝒏−1
24
12
4. Determining the sample size
• Practical considerations:
– The researcher and client discuss and agree on the desired
level confidence and the precision of the estimate.
– Since it is unlikely to be known, the true variability is
typically estimated based on judgment or through a pilot
study.
25
13