๐ Data Science Roadmap 2026
๐ Phase 2: Mathematics for Data Science
๐ Topic 9: Sampling & Sampling Techniques
Welcome back! ๐ In the previous lesson, you learned about Covariance and Correlation, which help us understand relationships between variables.
Now let's learn an important statistical concept: Sampling. In real-world Data Science, we often cannot collect or analyze data from every single individual in a population. Instead, we select a smaller group called a sample and use it to learn about the larger population.
๐น 1. What is a Population?
A population is the complete group we are interested in studying.
Example: Suppose a company has 100,000 customers โ those 100,000 customers represent the population. Other examples: All voters in a country, All employees in a company, All products manufactured by a factory, All transactions made by a bank.
๐น 2. What is a Sample?
A sample is a smaller subset selected from the population.
Example: Population = 100,000 customers, Sample = 1,000 customers. Instead of analyzing all 100,000, we analyze 1,000 carefully selected customers.
๐น 3. Population vs Sample
Population = Entire group, usually larger, more expensive to study, can be difficult to collect, described by population parameter.
Sample = Subset of the group, usually smaller, less expensive, easier to collect, described by sample statistic.
๐น 4. Parameter vs Statistic โญ
Parameter = A numerical value describing a population.
Example: Average income of all customers.
Statistic = A numerical value calculated from a sample.
Example: Average income of 1,000 sampled customers.
Simple rule: Population โ Parameter, Sample โ Statistic.
๐น 5. Why Do We Use Sampling?
Sampling can save: โ
Time, Money, Computational resources, Effort. It is especially useful when the population is extremely large.
Example: It would be impractical to interview every person in a country to estimate public opinion. Instead, researchers select a representative sample.
๐น 6. Simple Random Sampling โญ
In Simple Random Sampling, every member of the population has an equal chance of being selected.
Example: A company has 10,000 employees and randomly selects 500 employees for a survey.
๐น 7. Systematic Sampling
In Systematic Sampling, we select observations at a fixed interval.
Example: Population = 10,000 customers, Sample = 1,000, interval k = 10 โ select 10th, 20th, 30th, 40th... A random starting point is often chosen first.
๐น 8. Stratified Sampling โญ
In Stratified Sampling, we divide the population into meaningful groups called strata and then sample from each group.
Example: Engineering 50%, Sales 30%, HR 20%. For sample of 1,000 โ Engineering 500, Sales 300, HR 200. This helps ensure important subgroups are represented.
๐น 9. Cluster Sampling
In Cluster Sampling, the population is divided into naturally occurring groups called clusters. Instead of selecting individuals from every cluster, we randomly select some clusters and study members within those selected clusters.
Example: Schools can be treated as clusters โ randomly select schools โ survey students in selected schools.
๐น 10. Convenience Sampling
Convenience Sampling selects individuals who are easiest to reach.
2August 27, 2026 857 9
