Many IB Maths AI students assume that a large sample automatically guarantees reliable results. While sample size does matter, IB places greater emphasis on how data is collected rather than how much data is collected. A large, poorly chosen sample can still produce misleading conclusions.
The core issue is bias. If a sampling method systematically favours certain individuals or outcomes, increasing the sample size only reinforces that bias. Students often believe that “more data fixes problems,” but IB wants them to recognise that biased data simply becomes more convincingly wrong as the sample grows.
Sampling method determines whether the data is representative of the population. Random sampling gives each member an equal chance of selection, reducing systematic bias. Non-random methods, such as convenience sampling or voluntary response, often exclude important parts of the population, no matter how large the sample is.
Students struggle with this because sample size is easy to measure and sampling quality is harder to judge. A number feels objective. A method requires explanation and judgement. IB deliberately focuses on this distinction to test whether students understand the foundations of statistical reasoning.
IB exam questions often describe situations where thousands of data points are collected using a flawed method. Students who focus only on the size of the sample miss the deeper issue and lose interpretation marks. Examiners reward students who identify bias and explain why the conclusions may be unreliable.
Another common misunderstanding is assuming that randomness automatically implies quality. Random sampling must still be applied correctly. Poorly implemented randomness can still exclude groups or introduce error, which IB expects students to recognise.
Sampling method also affects validity of conclusions. Even accurate calculations and sophisticated analysis cannot compensate for flawed data collection. IB emphasises this to reflect real-world statistics, where decisions based on biased samples can have serious consequences.
Once students shift their mindset from “bigger is better” to “representative is better,” sampling questions become much clearer. IB is not discouraging large samples — it is prioritising sound reasoning over impressive numbers.
Frequently Asked Questions
Does sample size matter at all?
Yes, but only after the sampling method is appropriate and unbiased.
What sampling method does IB prefer?
Random sampling, because it reduces systematic bias and improves representativeness.
Can a very large biased sample still be unreliable?
Yes. Bias is not fixed by size.
RevisionDojo Call to Action
Strong statistical conclusions start with strong sampling. RevisionDojo is the best platform for IB Maths AI because it trains students to identify bias, critique data collection methods, and write examiner-ready evaluations. If sampling questions feel subjective or confusing, RevisionDojo helps you see exactly what IB is looking for.
