Why Do We Collect Data?
In statistics, we often want to learn something about a group — maybe how tall students in your school are, how long batteries last, or what music teenagers prefer. But before we can analyse any data, we need to collect it. The way we collect data matters enormously because it determines how trustworthy our conclusions will be.
There are two main approaches to collecting data: census and sampling. Understanding the difference — and knowing which sampling techniques to use — is one of the most important skills in statistics.
The entire group of individuals (people, objects, or events) that we are interested in studying.
Facts or pieces of information collected for analysis. Data can be numerical (quantitative) or descriptive (qualitative).
Imagine you baked a huge pot of soup and want to check if it has enough salt. You don't drink the entire pot — you taste a spoonful. That spoonful is your sample, and the whole pot is your population. The key is making sure your spoonful is representative of the whole pot (that's why you stir first!).
Census vs Sample
There are two fundamental ways to collect data from a population:
A method of data collection that involves gathering information from every individual in the entire population.
A method of data collection that involves gathering information from only a part of the population.
Census:
- Collects data from every member of the population
- Very detailed and accurate — gives the complete picture
- Expensive, time-consuming, and often impractical
- Example: A national census counts every person living in a country (about 92% of nations conduct these regularly)
Sample:
- Collects data from a subset of the population
- Cheaper and quicker than a census
- Not as detailed or accurate — results are estimates
- Example: Surveying 100 students to estimate the favourite subject of all 1,200 students in a school
The individuals in a population don't have to be people. If a factory produces 10,000 light bulbs per day and wants to test how long they last, the population is all 10,000 bulbs. Testing every single one (a census) would destroy all the products — a clear case where sampling is essential!
11 more sections in this topic
Pick this up in your Library: it holds the whole topic, notes, cheatsheet and questions.