In research, obtaining a representative sample from a population is crucial for drawing valid conclusions.

Two fundamental sampling techniques are simple random sampling and stratified random sampling. We
will see these two methods, highlighting their advantages, disadvantages, and providing illustrative
examples.

1. Simple Random Sampling (SRS)

Simple Random Sampling (SRS) is a sampling method where every member of the population has an
equal and independent chance of being selected for the sample. The selection process is entirely
random, without any pre-defined criteria or grouping.

The process for simple random sampling method of sampling are the following

1. Define the Population: Clearly identify the target population you want to study.

2. Create a Sampling Frame: Compile a complete and accurate list of all members of the population,
assigning each member a unique identifier (e.g., a number).

3. Random Selection: Use a random number generator or a similar method to select the desired
number of members from the sampling frame.

 Advantages of simple Random Sampling(SRS)

• Simplicity: SRS is conceptually straightforward and easy to implement.

• Lack of Bias (in Theory): If the sampling frame is accurate, SRS is unbiased because every member
has an equal chance of selection.

• Requires Minimal Prior Knowledge: You don't need extensive prior knowledge about the
population's characteristics.

 Disadvantages of simple Random Sampling(SRS)

• Potential for Unrepresentative Samples: Even with random selection, there's a chance the sample
may not accurately reflect the population's diversity, particularly for smaller sample sizes. Certain
subgroups may be over- or underrepresented due to chance.

• Ignores Population Structure: SRS treats the population as homogenous, ignoring any existing
subgroups that may be important to consider.

• High Variability: When the population has significant heterogeneity, SRS can lead to higher variability
in the sample estimates.
Example:

A researcher wants to survey the opinions of 100 students from a university with a total student
population of 2000. Using SRS:

1. Each student is assigned a unique number from 1 to 2000.

2. A random number selection is used to select 100 unique numbers between 1 and 2000.

3. The 100 students corresponding to the selected numbers are included in the sample.

2. Stratified Random Sampling

Stratified Random Sampling is a probability sampling method where the population is first divided into
homogenous subgroups called "strata" based on shared characteristics. Then, a simple random sample
is drawn from each stratum.

The process by which Stratified Random Sampling method of sampling is conducted are the following

1. Identify Relevant Strata: Determine the characteristics that are important to represent in the
sample (e.g., age, gender, ethnicity, income level).

2. Divide Population into Strata: Divide the population into mutually exclusive and collectively
exhaustive subgroups (strata) based on the chosen characteristics.

3. Determine Sample Size for Each Stratum: Decide on the sample size for each stratum. This can be
done using:

 Proportional Allocation: Sample size in each stratum is proportional to its size in the
population.

 Equal Allocation: Same sample size is drawn from each stratum, regardless of its size in the
population. This is useful when studying smaller subgroups.

 Optimal Allocation: Takes into account the variability within each stratum to minimize
sampling error.

4. Random Selection within Strata: Use simple random sampling within each stratum to select the
required number of members.
  Advantages of Stratified Random sampling

• Increased Representativeness: Ensures that all relevant subgroups are represented in the sample,
reflecting the population's composition more accurately.

• Reduced Sampling Error: Stratification can reduce sampling error, especially when the characteristic
used for stratification is related to the variable being studied. This leads to more precise estimates.

• Allows for Subgroup Analysis: Allows for separate analysis and comparisons between different
strata.

• Greater Statistical Power: Can increase the statistical power of the study, making it easier to detect
significant differences.

 Disadvantages Stratified Random Sampling

• Requires Prior Knowledge: Requires knowledge of the population's characteristics to identify and
define the appropriate strata.

• More Complex and Time-Consuming: More complex to plan and execute than simple random
sampling.

• Misclassification Errors: If individuals are incorrectly assigned to a stratum, it can bias the results.

• Can be More Expensive: The increased complexity can translate into higher costs.

Example:

In a research aimed at assessing student satisfaction across various departments, a university employs
stratified random sampling. The population consists of 4,000 students divided into four departments:
Engineering (1,200 students), Business (800 students), Arts (600 students), and Sciences (1,400
students). To ensure proportional representation, the university plans to survey a total of 400 students,
calculating the sample sizes for each department as follows:

• Engineering: 1200/4000 × 400 = 120 students

• Business: 800/4000 × 400 = 80 students

• Arts: 600/4000 × 400 = 60 students

• Sciences: 1400/4000 × 400 = 140 students

Random samples are then selected from each department, allowing the university to gather
comprehensive feedback that accurately reflects the diverse experiences of its student body. This
approach not only enhances representation but also enables detailed insights into satisfaction levels
within each department, facilitating targeted improvements based on specific needs.

 Conclusion

Both simple random sampling and stratified random sampling are valuable sampling techniques. Simple
random sampling is easy to implement but may not always produce representative samples. Stratified
random sampling, while more complex, offers the advantage of ensuring representation of important
subgroups and can lead to more precise and reliable results. The choice between these methods
depends on the research objectives, the characteristics of the population, and the available resources.
When specific subgroups are of interest or need to be accurately represented, stratified random
sampling is often the preferred method.