Sampling
Sampling
What is sampling
• Research involves collecting investigating issues related to
large populations.
Subject
Sampling terminology
• Statistic
• The characteristics of sample.
• Sample mean = X
• Sample Standard Deviation = S
• Sample Variance = S2
• Parameter
• The characteristics of population
• Population Mean = μ
• Population Standard Deviation = σ
• Population Variance = σ2
• Representativeness of Sample
• The sample characteristics should be close to population characteristics
Stages in sampling process
• Define the target population
• Select a population/sampling frame (if available)
• Determine sampling method (Probability or non-
probability.)
• Determine sample size
• Select actual samples
• Conduct field work.
Probability Nonprobability
Sampling Sampling
• For example:
• Let us say there are 4,000 elements in the population and We
need a sample of 300.
• We need the population frame containing the names of all the
4000 elements. We put all those 4000 names in a box and
randomly draw one.
• The first name drawn will have a 1/4,000 chance of being drawn
• The next one a 1/3999 chance of being drawn, and so on.
• A computer program can generate random numbers for us.
Simple Random Sampling
• simple random sampling, has the least bias and
offers the most generalizability.
• Let us say that the random number is 7, then houses numbered 7, 14, 21,
28, and so on, would be sampled until the 35 houses are selected.
Stratified Random
Sampling
• We divide the population into two or more relevant
strata (groups) based on some attributes.
1. Proportionate Stratified
The number of sampling units drawn from each stratum
is in proportion to the population size of that stratum.
2. Disproportionate Stratified
The sample size for each stratum is allocated according
to analytical considerations.
Proportionate and Disproportionate
Stratified Random Sampling
Cluster sampling
• An economically efficient sampling technique in which the primary
sampling unit is not the individual element in the population but a large
cluster of elements; clusters are selected randomly.
• For cluster sampling your sampling frame is the complete list of clusters
rather than a complete list of individual cases within the population.
• You then select a few clusters, normally using simple random sampling.
• Data are then collected from every case within the selected clusters.
• This means that the findings from the study of the sample
cannot be confidently generalized to the population.
• Either because they are the only ones who have it, or conform
to some criteria set by the researcher.
• Used for Populations that are difficult to access directly due to privacy
concerns, social stigma, or legal reasons.
• Situations where trust is essential for accessing participants.
• Examples:
• Studying drug users
• Undocumented migrants
• Studying emerging entreprenures