An Overview of Sampling Methods: Types, Uses, and Importance

This report provides a detailed explanation of sampling methods used in statistics, highlighting their importance in making inferences about populations based on selected observations. It covers various sampling techniques, including random sampling, simple random sampling, stratified sampling, quota sampling, cluster sampling, and systematic sampling, detailing how each method is applied and their respective advantages. The report emphasizes the accuracy, cost-effectiveness, and reduced bias achieved through sampling compared to analyzing entire populations, advocating for simple random sampling as a particularly effective method due to its accuracy, lack of bias, and cost efficiency. Real-life scenarios are provided to illustrate the application of these methods.

Sampling
Meaning of sampling-it’s a procedure in the field of statistics that involves the selecting
specified observations that will help in making inferences today and in future. Rather than
gathering all the information, a sample is used to represent the entire population and
inferences is made out of it.
Importance of sampling
a) Sampling is done so as to produce accurate results
b) Its desirable to do sampling as less costly, if it was to be done in a whole population it
would have been so expensive
c) It avoids biasness
Methods of sampling
 Random sampling- in random sample every member of the population stands an equal
chance to be selected, and there should be no designed formula when choosing the
sample. For example, if you want to do a survey on student, computer is used to generate
random students, it is from the randomly selected students that a survey will be done.
 Simple random sampling-in this sampling method each sample in a population of
specified size say n is chosen, so that every sample of the size n in that population have
equal chance to be selected
 Stratified sampling-in stratified sampling a population to be considered is divided into
several groups. From those groups, a random sample with sample sizes directly
proportional to the group size is then taken. For example, if we have a population of 400
teachers, 60 teachers are randomly selected for the age of between 26-30 years, 140
teachers from the age of between 31-35 years, 120 teachers from the age of 36-40 and 80
teachers from the age of 41-45 years
 Quota sampling-this sampling method is almost similar to stratified sampling but not as
samples from each group divided from the population are collected until a convincing or
a desired quota is arrived at
 Cluster sampling- in this method of sampling of a population to be researched on is
subdivided into groups called clusters, then a set of clusters are picked to be in an
individual sample. For example, if you want to know how product sales in 150 stores,
researchers may choose to 100 stores to do the research
 Systematic sampling- in systematic sampling, say for a specified population nth item or a
member is chosen to be in the sample. For example, if you want to conduct a survey on a
department, one doing the survey may pick third student in an enrollment list of every
class as the sample
The best sampling method to use is simple random sampling as it is more accurate, there will
be no biasness as sample is picked randomly and it is less costly compared to other method.
Real life scenario is given on the method section

REFERENCE
Smith, A. F., & Gelfand, A. E. (2016). Bayesian statistics without tears: a sampling–resampling
perspective. The American Statistician, 46(2), 84-88.
Fuller, W. A. (2011). Sampling statistics (Vol. 560). John Wiley & Sons.