Question 1

What is the difference between a one-tailed and two-tailed hypothesis test?

Accepted Answer

A one-tailed test is used when the alternative hypothesis specifies a direction (e.g., greater than or less than). A two-tailed test is used when the alternative hypothesis simply states that the parameter is different (not equal). In a one-tailed test, the critical region is all in one tail of the distribution, while in a two-tailed test, it is split equally between both tails. The choice depends on the research question: if you only care about an increase, use one-tailed; if you care about any change, use two-tailed.

Question 2

How do I find the critical region for a binomial hypothesis test?

Accepted Answer

For a binomial test with parameters n and p under H₀, you need to find the critical values using the cumulative distribution function. For a lower-tail test (H₁: p < p₀), find the largest integer c such that P(X ≤ c) ≤ α. For an upper-tail test (H₁: p > p₀), find the smallest integer c such that P(X ≥ c) ≤ α. For a two-tailed test, split α into two halves (α/2 in each tail) and find both critical values. Use binomial tables or a calculator with inverse binomial functions.

Question 3

What is a Type I error and how does it relate to the significance level?

Accepted Answer

A Type I error occurs when you reject the null hypothesis when it is actually true. The probability of making a Type I error is exactly the significance level α. For example, if you use a 5% significance level, there is a 5% chance of rejecting a true H₀. This is why we choose a small α – to keep the risk of a false positive low. In contrast, a Type II error is failing to reject a false H₀, and its probability is denoted β.

Question 4

How do I interpret a p-value in a hypothesis test?

Accepted Answer

The p-value is the probability of obtaining a test statistic as extreme as, or more extreme than, the observed value, assuming the null hypothesis is true. If the p-value is less than the significance level α, you reject H₀ because the observed result is unlikely under H₀. For example, if p = 0.03 and α = 0.05, you reject H₀, concluding there is evidence for the alternative. If p > α, you do not reject H₀. The p-value does not tell you the probability that H₀ is true.

Question 5

When should I use a normal distribution test instead of a binomial test?

Accepted Answer

Use a binomial test when the data come from a binomial setting (fixed number of independent trials, two outcomes, constant probability). Use a normal distribution test when you are testing a population mean and the sample size is large enough (n ≥ 30) or the population is normally distributed. For proportions, the binomial test is exact, but for large samples you can approximate using a normal distribution (with continuity correction). In AQA A-Level, you will use binomial tests for proportions and normal tests for means.

Question 6

What does 'reject H₀' actually mean in the context of a problem?

Accepted Answer

Rejecting H₀ means that the sample evidence provides sufficient evidence to support the alternative hypothesis at the chosen significance level. It does not prove H₁ is true; it just suggests that the data are inconsistent with H₀. For example, if testing whether a new drug is effective, rejecting H₀ (that the drug has no effect) indicates that the data show a statistically significant effect, but there is still a small chance (α) that this conclusion is wrong.

O: Statistical hypothesis testing

Topic Overview

Key Concepts

What You Need to Demonstrate

Assessment Criteria

Assessment Guidance

Common Mistakes

Frequently Asked Questions

Before You Start

Key Terminology

Ready to learn?

Related Topics in AQA vocational Mathematics

A: Proof

B: Algebra and functions

C: Coordinate geometry in the ( x , y ) plane

D: Sequences and series

How to Revise O: Statistical hypothesis testing — AQA A-Level Mathematics

Examiner Tips for O: Statistical hypothesis testing

Common Mistakes in O: Statistical hypothesis testing

Key Marking Points