Skip to content
Statistics InferenceStatistics Inference

Null and Alternative Hypotheses Explained

What the null and alternative hypotheses are, how to write them, one- vs two-tailed, and Type I and Type II errors — with a worked example.

6 min read · Reviewed August 2026

What the null and alternative hypotheses are

Every hypothesis test starts with two competing statements. The null hypothesis (H₀) is the default position of “no effect” or “no difference”. The alternative hypothesis (H₁ or Hₐ) is the claim you are actually trying to find evidence for.

A test never “proves” the alternative. Instead it asks whether the data gives enough evidence to reject the null. If it does, you accept the alternative; if not, you fail to reject the null.

How to write them

The null always contains equality; the alternative captures what you want to detect. For a test about a population mean μ against a target value μ₀:

TestNull (H₀)Alternative (H₁)
Two-tailedμ = μ₀μ ≠ μ₀
One-tailed (greater)μ ≤ μ₀μ > μ₀
One-tailed (less)μ ≥ μ₀μ < μ₀

Type I and Type II errors

Because a test decides from limited data, it can be wrong in two ways:

ErrorWhat happensProbability
Type IReject a true null (false positive)α (significance level)
Type IIFail to reject a false null (false negative)β
The power of a test is 1 − β: the chance of correctly detecting a real effect. Larger samples reduce both error rates.

The testing process

  1. State H₀ and H₁ and choose a significance level α (often 0.05).
  2. Collect data and compute a test statistic (e.g. a t- or z-score).
  3. Find the p-value for that statistic.
  4. Reject H₀ if p ≤ α; otherwise fail to reject it.
  5. State the conclusion in the context of the problem.

A worked example

A factory claims its bags weigh 500 g. You suspect they are underfilled. You would write H₀: μ ≥ 500 and H₁: μ < 500 (a one-tailed test). You weigh a sample, compute a t-statistic and its p-value, and if that p-value is at or below 0.05 you reject H₀ and conclude the bags are underfilled.

Frequently asked questions

What is a null hypothesis in simple terms?

It is the default assumption that there is no effect, no difference, or no relationship. A hypothesis test looks for evidence strong enough to reject this default in favour of the alternative.

What is the difference between the null and alternative hypothesis?

The null hypothesis (H₀) states there is no effect and always contains an equality. The alternative hypothesis (H₁) is the claim you want to support — that there is a difference, an increase, or a decrease.

Can you prove the null hypothesis?

No. You can only fail to reject it. Failing to reject the null means the data did not provide enough evidence against it — not that it is definitely true.