A-Level Maths: O1-03 [Hypothesis Testing: One-Tail or Two-Tail Test?]

Summary

This video explains how to determine whether a hypothesis test is one-tailed or two-tailed based on the alternative hypothesis. It provides examples using binomial hypothesis testing and discusses how the significance level is applied differently in each type of test.

Highlights

Identifying One-Tail vs. Two-Tail Tests00:00:00

When performing a hypothesis test, it is crucial to identify if it's a one-tail or a two-tail test. This distinction is primarily inferred from the null and alternative hypotheses, especially the alternative hypothesis.

One-Tail Test Examples00:00:21

In a binomial hypothesis test, the null hypothesis (H0) states that the probability of an event happening is as expected, for instance, p = 0.6. A one-tail alternative hypothesis (H1) suggests the probability has either decreased (p < 0.6) or increased (p > 0.6).

Two-Tail Test Example00:01:15

If the alternative hypothesis suggests the probability is simply 'different to' or 'not equal to' 0.6 (p ≠ 0.6), it indicates a two-tailed test. This means we are looking for deviations in both directions (higher or lower).

Significance Levels in Two-Tail Tests00:01:46

In a two-tailed test, the significance level (e.g., 10%) is split across both tails. For example, a 10% significance level would be divided into 5% for the lower end and 5% for the upper end, unlike one-tail tests where the entire significance level is in one tail.

Key Indicators for Test Type00:02:46

To explain the alternative hypothesis, look for keywords like 'less than', 'greater than', 'different to', or 'not equal to' to determine if it's a one-tailed or two-tailed test.