What's the difference between a one-tailed and a two-tailed test?

A two-tailed test checks for a difference in either direction (e.g., $H_1: \mu \neq 50$). The significance level $\alpha$ is split between the two tails. A one-tailed test checks for a difference in a specific direction (e.g., $H_1: \mu > 50$ or $H_1: \mu < 50$). The entire significance level $\alpha$ is in one tail.

Why do we use n-1 for the degrees of freedom in a t-test?

It relates to the calculation of the sample variance, $s^2$. When we calculate the sum of squared deviations from the sample mean, $\sum(x_i - \bar{x})^2$, only $n-1$ of these deviations are free to vary. Once the first $n-1$ values and the sample mean are known, the last value is fixed. This 'loss' of one degree of freedom is reflected in the t-distribution.

What if the population isn't normal and the sample size is small?

If the sample size is small and you cannot assume the population is normal, neither the z-test nor the t-test is appropriate. In this situation, you would need to use non-parametric tests (e.g., a sign test or Wilcoxon signed-rank test), which are covered in other parts of the syllabus and do not assume a particular distribution for the population.

How do I know if a sample size is 'large' enough to use the normal distribution?

A common rule of thumb in A-Level Further Mathematics is that a sample size $n > 30$ is considered large enough for the Central Limit Theorem to apply, allowing you to use the normal distribution even if the population variance is unknown. For exams, if $n$ is around this value or higher, this is the expected approach.

Where can I learn Inference using normal and t-distributions for Cambridge 9231?

This free lesson on MarkScheme covers syllabus point 4.2 (Inference using normal and t-distributions) for Cambridge A-Level Further Mathematics. It includes visual revision, key points, and links to real past-paper questions with mark-scheme marking at markscheme.app/courses/9231/4-2-inference-using-normal-and-t-distributions.

Is Inference using normal and t-distributions (4.2) on 9231 free to study?

Yes. The Further Mathematics 9231 course on MarkScheme is 100% free — including premium visual lessons, exam tips, and past-paper marking. No paywall for Inference using normal and t-distributions.

Inference using normal and t-distributions…

Inference using normal and t-distributions

In the real world, we rarely have access to data for an entire population. We can't weigh every apple from an orchard or measure the battery life of every phone produced. Statistical inference provides a powerful framework for making reliable conclusions about a whole population based on just a small sample. This lesson focuses on the population mean, $\mu$ , and introduces two key tools: the normal distribution and the t-distribution. Mastering when and how to use them is fundamental to drawing valid conclusions from data.

BY THE END, YOU CAN…

1Formulate hypotheses and carry out a hypothesis test for a population mean using the normal distribution.
2Formulate hypotheses and carry out a hypothesis test for a population mean using the t-distribution.
3Calculate and interpret a confidence interval for a population mean using both the normal and t-distributions.
4Understand the conditions under which each distribution is appropriate for inference.

In simple terms

A friendly intro before the formal notes — no formulas yet.

Guessing with Confidence

We use data from a small sample to make an educated guess, or 'inference', about an entire population. The choice between the normal and t-distribution depends on whether we know the population's true variance and how large our sample is.

THINK OF IT LIKE…

Imagine you're a food critic trying to rate a huge pot of soup. You can't eat the whole thing, so you take a spoonful (a sample). Based on that spoonful, you infer the taste of the entire pot (the population). If you know the chef's recipe perfectly (known population variance), you can be quite precise. If you don't (unknown variance), you have to be a bit more cautious with your judgement, which is what the t-distribution helps us do – it gives a slightly wider, more conservative range for our conclusions.

1
Identify the parameter of interest (population mean, μ) and the sample statistics (mean x̄, variance s², size n).
2
Choose the distribution: Use the Normal distribution if the population variance σ² is known, or if the sample size n is large. Use the t-distribution if σ² is unknown and n is small.
3
For a hypothesis test, state the null (H₀) and alternative (H₁) hypotheses, then calculate the test statistic (z or t).
4
For a confidence interval, find the appropriate critical value (z* or t*) and calculate the interval: sample mean ± (critical value) × (standard error).

Explore the concept

Use the live diagram and synced steps — play it or tap a step card to walk through.

Key formulas

Tap any symbol to reveal exactly what it means and its units.

$Z = \frac{\bar{X} - \mu_0}{\sigma/\sqrt{n}}$

Tap a symbol — great for exam definitions

$\bar{x} \pm z^* \frac{\sigma}{\sqrt{n}}$

Tap a symbol — great for exam definitions

Full topic notes

Formal explanation with the rigour you need for the exam.

Choosing Your Distribution: Normal vs. t-distribution

The choice between using the normal distribution and the t-distribution is a critical first step. It depends on what you know about the population and the size of your sample. The t-distribution is like a 'cautious' version of the normal distribution, with heavier tails to account for the extra uncertainty we have when the population variance is unknown and our sample is small.

Population Variance $\sigma^2$ Known: If you know the true variance of the population, you should always use the normal distribution for inference on the mean, provided the underlying population is normal or the sample size is large (Central Limit Theorem).
Population Variance $\sigma^2$ Unknown & Sample Size Large ( $n > 30$ ): If you don't know $\sigma^2$ but have a large sample, the Central Limit Theorem allows you to use the normal distribution. You use the unbiased sample variance $s^2$ as an estimate for $\sigma^2$ .
Population Variance $\sigma^2$ Unknown & Sample Size Small ( $n \le 30$ ): If you don't know $\sigma^2$ and have a small sample, you must use the t-distribution. This is conditional on the assumption that the underlying population from which the sample is drawn is normally distributed.

Hypothesis Testing for a Population Mean

A hypothesis test allows us to assess the evidence for a claim about a population parameter. For the mean $\mu$ , we start with a null hypothesis ( $H_0$ ), which is a statement of no effect (e.g., $\mu = 50$ ), and an alternative hypothesis ( $H_1$ ), which is what we are trying to find evidence for (e.g., $\mu \neq 50$ , $\mu > 50$ , or $\mu < 50$ ). We then calculate a test statistic from our sample and compare it to a critical value from the appropriate distribution to decide whether to reject $H_0$ .

Test Statistic (Normal): $Z = \frac{\bar{X} - \mu_0}{\sigma/\sqrt{n}}$ \ Test Statistic (t-distribution): $T = \frac{\bar{X} - \mu_0}{s/\sqrt{n}}$ with $v = n-1$ degrees of freedom.

Confidence Intervals for a Population Mean

A confidence interval provides a range of plausible values for the population mean, based on our sample data. A 95% confidence interval means that if we were to repeat our sampling process an infinite number of times, 95% of the intervals we construct would contain the true population mean. The width of the interval depends on the confidence level, the sample size, and the variation in the data.

Confidence Interval (Normal): $\bar{x} \pm z^* \frac{\sigma}{\sqrt{n}}$ \ Confidence Interval (t-distribution): $\bar{x} \pm t^* \frac{s}{\sqrt{n}}$

Worked examples

See the formulas applied — reveal one step at a time, like the exam.

EXAMPLE 1

A coffee machine is supposed to dispense a mean volume of 200 ml. The volume dispensed is believed to be normally distributed. A sample of 8 cups is taken, and the volumes are measured. The sample mean is found to be 197 ml, and the unbiased estimate of the population variance is $s^2 = 36\text{ ml}^2$ . Test, at the 5% significance level, whether the mean volume dispensed is less than 200 ml.

1
Let $\mu$ be the population mean volume of coffee dispensed.
1. State Hypotheses:
$H_0: \mu = 200$
$H_1: \mu < 200$
This is a one-tailed test.\

EXAMPLE 2

The reaction times of 50 randomly selected drivers are measured. The sample mean reaction time is 0.83 seconds. Assume the population standard deviation of reaction times is known to be 0.15 seconds. Calculate a 99% confidence interval for the mean reaction time of all drivers.

1
Let $\mu$ be the population mean reaction time.
1. Identify Information and Choose Distribution:
Sample mean, $\bar{x} = 0.83$ .
Population standard deviation, $\sigma = 0.15$ .
Sample size, $n = 50$ .
Confidence level = 99%.
Since the population standard deviation $\sigma$ is known, we use the normal distribution.\

How it all connects

The big idea sits in the middle — tap a linked idea to explore the link.

MAIN IDEAInference using normal and t-distributions

Tap a linked idea to see how it connects back to the main topic — that connection is what examiners reward.

Glossary

Try to recall each definition before you reveal it.

Quick check

Answer in your head first — then tap to check. No pressure.

Revision flashcards

Flip the card. Test yourself before the exam.

QUESTION · 1 / 12

What is statistical inference?

TAP OR SPACE TO FLIP

ANSWER

The process of using data from a sample to deduce properties of an underlying population.

TAP OR SPACE TO FLIP BACK

1 / 12 · ← → space

Key takeaways

Review these before you close the topic — retrieval beats re-reading.

✓
Population Variance $\sigma^2$ Known: If you know the true variance of the population, you should always use the normal distribution for inference on the mean, provided the underlying population is normal or the sample size is large (Central Limit Theorem).
✓
Population Variance $\sigma^2$ Unknown & Sample Size Large ( $n > 30$ ): If you don't know $\sigma^2$ but have a large sample, the Central Limit Theorem allows you to use the normal distribution. You use the unbiased sample variance $s^2$ as an estimate for $\sigma^2$ .
✓
Population Variance $\sigma^2$ Unknown & Sample Size Small ( $n \le 30$ ): If you don't know $\sigma^2$ and have a small sample, you must use the t-distribution. This is conditional on the assumption that the underlying population from which the sample is drawn is normally distributed.

Practice — then mark it

The whole point: a real Cambridge question, marked mark-by-mark.

Real past paper[0]

Practice Questions

Do it on paper → mark itMARKED MARK-BY-MARK · B1 / M1 / A1 · OFFICIAL SCHEME

Extra simulations & links

PhET, GeoGebra and other curated tools — open in a new tab.

Frequently asked

✓

Checkpoint

One marked question is worth ten re-reads — close the loop before you move on.

Checkpoint

Reading it isn’t knowing it — prove it.

Before you move on: do Practice Questions on paper, snap a photo, and get examiner-style feedback on exactly where you win and lose marks.

Attempt & get marked →Takes about a minute · you’ll land back on this lesson

← PREVIOUS4.1 Continuous random variables NEXT →4.3 χ²-tests

Inference using normal and t-distributions

BY THE END, YOU CAN…

1Formulate hypotheses and carry out a hypothesis test for a population mean using the normal distribution.
2Formulate hypotheses and carry out a hypothesis test for a population mean using the t-distribution.
3Calculate and interpret a confidence interval for a population mean using both the normal and t-distributions.
4Understand the conditions under which each distribution is appropriate for inference.

In simple terms

A friendly intro before the formal notes — no formulas yet.

Guessing with Confidence

THINK OF IT LIKE…

1
Identify the parameter of interest (population mean, μ) and the sample statistics (mean x̄, variance s², size n).
2
Choose the distribution: Use the Normal distribution if the population variance σ² is known, or if the sample size n is large. Use the t-distribution if σ² is unknown and n is small.
3
For a hypothesis test, state the null (H₀) and alternative (H₁) hypotheses, then calculate the test statistic (z or t).
4
For a confidence interval, find the appropriate critical value (z* or t*) and calculate the interval: sample mean ± (critical value) × (standard error).

Explore the concept

Use the live diagram and synced steps — play it or tap a step card to walk through.

Key formulas

Tap any symbol to reveal exactly what it means and its units.

$Z = \frac{\bar{X} - \mu_0}{\sigma/\sqrt{n}}$

Tap a symbol — great for exam definitions

$\bar{x} \pm z^* \frac{\sigma}{\sqrt{n}}$

Tap a symbol — great for exam definitions

Full topic notes

Formal explanation with the rigour you need for the exam.

Choosing Your Distribution: Normal vs. t-distribution

Population Variance $\sigma^2$ Known: If you know the true variance of the population, you should always use the normal distribution for inference on the mean, provided the underlying population is normal or the sample size is large (Central Limit Theorem).
Population Variance $\sigma^2$ Unknown & Sample Size Large ( $n > 30$ ): If you don't know $\sigma^2$ but have a large sample, the Central Limit Theorem allows you to use the normal distribution. You use the unbiased sample variance $s^2$ as an estimate for $\sigma^2$ .
Population Variance $\sigma^2$ Unknown & Sample Size Small ( $n \le 30$ ): If you don't know $\sigma^2$ and have a small sample, you must use the t-distribution. This is conditional on the assumption that the underlying population from which the sample is drawn is normally distributed.

Hypothesis Testing for a Population Mean

Test Statistic (Normal): $Z = \frac{\bar{X} - \mu_0}{\sigma/\sqrt{n}}$ \ Test Statistic (t-distribution): $T = \frac{\bar{X} - \mu_0}{s/\sqrt{n}}$ with $v = n-1$ degrees of freedom.

Confidence Intervals for a Population Mean

Confidence Interval (Normal): $\bar{x} \pm z^* \frac{\sigma}{\sqrt{n}}$ \ Confidence Interval (t-distribution): $\bar{x} \pm t^* \frac{s}{\sqrt{n}}$

Worked examples

See the formulas applied — reveal one step at a time, like the exam.

EXAMPLE 1

1
Let $\mu$ be the population mean volume of coffee dispensed.
1. State Hypotheses:
$H_0: \mu = 200$
$H_1: \mu < 200$
This is a one-tailed test.\

EXAMPLE 2

1
Let $\mu$ be the population mean reaction time.
1. Identify Information and Choose Distribution:
Sample mean, $\bar{x} = 0.83$ .
Population standard deviation, $\sigma = 0.15$ .
Sample size, $n = 50$ .
Confidence level = 99%.
Since the population standard deviation $\sigma$ is known, we use the normal distribution.\

How it all connects

The big idea sits in the middle — tap a linked idea to explore the link.

MAIN IDEAInference using normal and t-distributions

Tap a linked idea to see how it connects back to the main topic — that connection is what examiners reward.

Glossary

Try to recall each definition before you reveal it.

Quick check

Answer in your head first — then tap to check. No pressure.

Revision flashcards

Flip the card. Test yourself before the exam.

QUESTION · 1 / 12

What is statistical inference?

TAP OR SPACE TO FLIP

ANSWER

The process of using data from a sample to deduce properties of an underlying population.

TAP OR SPACE TO FLIP BACK

1 / 12 · ← → space

Key takeaways

Review these before you close the topic — retrieval beats re-reading.

✓
Population Variance $\sigma^2$ Known: If you know the true variance of the population, you should always use the normal distribution for inference on the mean, provided the underlying population is normal or the sample size is large (Central Limit Theorem).
✓
Population Variance $\sigma^2$ Unknown & Sample Size Large ( $n > 30$ ): If you don't know $\sigma^2$ but have a large sample, the Central Limit Theorem allows you to use the normal distribution. You use the unbiased sample variance $s^2$ as an estimate for $\sigma^2$ .
✓
Population Variance $\sigma^2$ Unknown & Sample Size Small ( $n \le 30$ ): If you don't know $\sigma^2$ and have a small sample, you must use the t-distribution. This is conditional on the assumption that the underlying population from which the sample is drawn is normally distributed.

Practice — then mark it

The whole point: a real Cambridge question, marked mark-by-mark.

Real past paper[0]

Practice Questions

Do it on paper → mark itMARKED MARK-BY-MARK · B1 / M1 / A1 · OFFICIAL SCHEME

Extra simulations & links

PhET, GeoGebra and other curated tools — open in a new tab.

Frequently asked

✓

Checkpoint

One marked question is worth ten re-reads — close the loop before you move on.

Checkpoint

Reading it isn’t knowing it — prove it.

Before you move on: do Practice Questions on paper, snap a photo, and get examiner-style feedback on exactly where you win and lose marks.

Attempt & get marked →Takes about a minute · you’ll land back on this lesson

← PREVIOUS4.1 Continuous random variables NEXT →4.3 χ²-tests

Revise Inference using normal and t-distributions for Cambridge 9231 (4.2)

In simple terms

Explore the concept

Key formulas

Full topic notes

Choosing Your Distribution: Normal vs. t-distribution

Hypothesis Testing for a Population Mean

Confidence Intervals for a Population Mean

Worked examples

How it all connects

Glossary

Quick check

Revision flashcards

Key takeaways

Practice — then mark it

Practice Questions

Extra simulations & links

Frequently asked

Checkpoint

Reading it isn’t knowing it — prove it.

In simple terms

Explore the concept

Key formulas

Full topic notes

Choosing Your Distribution: Normal vs. t-distribution

Hypothesis Testing for a Population Mean

Confidence Intervals for a Population Mean

Worked examples

How it all connects

Glossary

Quick check

Revision flashcards

Key takeaways

Practice — then mark it

Practice Questions

Extra simulations & links

Frequently asked

Checkpoint

Reading it isn’t knowing it — prove it.

Discuss Inference using normal and t-distributions