Sampling

• Sampling is the act of selecting a smaller number of subjects (a sample) from a population to represent the whole population.
• A study sample is a subset of the accessible population that participates in the study.
• The results of the sample are assumed to represent the entire population.
• Sampling is not necessary if the population is small.
• A larger sample size generally leads to a higher level of accuracy.

Importance of Sampling

• Sampling is done to effectively manage large and dispersed populations.
• It minimizes the cost of conducting a study.
• It saves time.
• It can improve the accuracy of findings.
• It allows for less demanding studies.
• It can reduce the level of destruction when sampling involves destroying items.

Sampling Methods

• Sampling methods are procedures for selecting sample elements from a population.
• The choice of a sampling method depends on factors such as the type of population, the desired degree of accuracy, available resources, the homogeneity of the population, and the urgency of the findings.
• Sampling methods are generally categorized into random and non-random methods.

Random Sampling Methods

• In random sampling, every element in the population has the same probability of selection.
• Advantages:
  • Offers equal chances to all members of the population to be selected.
  • Eliminates bias.
  • Improves the validity of the study.
  • Easy to administer.
  • Provides statistical means of manipulating data.
• Disadvantages:
  • Requires a sample frame of all members of a finite population.
  • May lead to unproportional representation of strata in a heterogeneous population.
  • Types of Random Sampling:
    • Simple Random Sampling: Every object has the same probability of being chosen. Can be done using a lottery method or a random number table.
    • Stratified Random Sampling: The population is divided into subgroups (strata) before drawing the sample. The percentage of subgroups in the sample must be the same as in the population.
    • Systematic Sampling: Elements are selected at regular intervals from an ordered list. The starting element is chosen randomly to avoid bias. Best method for a big, homogenous population, and easy to administer.
    • Cluster Sampling: The population is divided into groups (clusters), and one or more clusters are chosen at random. Then, everyone within the chosen cluster is sampled. Useful when a list of subjects is not possible, instead, a map of an area can be used.
    • Multi-stage sampling: A technique where several levels of cluster selection are applied before reaching the final sample elements. Researchers randomly select elements from each cluster, but not all of the elements in a selected cluster.

Non-Random Sampling Methods

• In non-random sampling, some elements of the population have no chance of selection, or the probability of selection cannot be accurately determined.
• Primarily used in qualitative studies.
• Advantages:
  • They are cheap.
  • They have a less complicated approach to sampling.
  • They offer faster results.
  • They usually do not need a list of all members of the population.
• Disadvantages:
  • Prone to human error and bias.
  • Better applied when research findings are not generalized beyond the sample.
  • Statistical analysis of sample results is not appropriate.
  • Types of Non-Random Sampling:
    • Convenient sampling: The sample is selected based on the convenience of the researcher and how accessible, convenient, and cooperative a subject may be.
    • Purposive/Judgmental sampling: Sampling depends entirely on the researcher’s interest and judgment.
    • Snowball sampling: Respondents are recommended by colleagues who know they can offer good data.
    • Quota sampling: A non-probability version of stratified sampling where the population is segmented into subgroups, and judgment is used to select subjects from each segment based on a specified proportion.
    • Accidental sampling: Respondents are not deliberately selected but are incidental to prevailing circumstances.

Sampling Errors

• Sampling errors arise from drawing wrong conclusions or generalizing issues based on findings from a small sample.
• Errors are less when the sample size is large and sampling is random.
• Non-probability sampling does not allow the estimation of sampling error.
• Types of errors:
  • Random error: A wrong result due to chance, can be overcome by increasing the sample size.
  • Systemic error: A wrong result due to bias.