Two-tailed test
A two-sided test is a hypothesis test in which sufficiently extreme results in either direction from the null value count as evidence against the null hypothesis.
Grokking Statistics
A two-tailed hypothesis test treats unusually large deviations in either direction from the null value as evidence against the null hypothesis.
- How it is used
- Tests whether sample evidence supports any difference from a hypothesized population value.
- How deep it goes
- Defines hypotheses, tail allocation, critical regions, and p-value decisions, then applies the procedure to measured data.
- Examples
- Uses a 142-gram potato-chip label, 41 sampled bags, and a 140.2-gram sample mean.
- What you can do after
- Apply it via Python and SciPy to calculate a test statistic, critical values, and a hypothesis-testing decision.
Timeless Algorithms, The Foundational Ideas
A two-tailed test is a hypothesis test whose rejection region includes extreme values in both directions of the test-statistic distribution.
- How it is used
- Selects a test direction when a quality-control question treats departures above and below a target as meaningful.
- How deep it goes
- Defines the choice through hypotheses and a practical example, while deferring the decision to reject the null based on sample evidence.
- Examples
- Uses a beverage batch with a 12-ounce target to contrast concern about underfilling and overfilling.
- What you can do after
- Apply it by stating hypotheses and choosing a two-tailed test before examining sample data when departures in either direction matter.
Read how Timeless Algorithms, The Foundational Ideas explains two-tailed test →
What to know first
- student's t-distributionStudent’s t-distribution is a family of continuous probability distributions with heavier tails than the normal distribution, used in inference when variability is estimated from data.
Related concepts
- one-sided testcontrasts with · A one-sided test is a hypothesis test whose alternative hypothesis and rejection region concern a departure from the null in one prespecified direction.
- hypothesis testingkind of · Hypothesis testing is a formal statistical procedure for evaluating evidence from observed data about a specified hypothesis, often a null hypothesis.
- meanuses · The mean is a measure of central location equal to the arithmetic average of numerical observations, or the probability-weighted average of a random variable’s possible values.
- alternative hypothesisuses · An alternative hypothesis is a statistical proposition that contrasts with the null hypothesis by asserting an effect, difference, relationship, or other departure.
- null hypothesisuses · A null hypothesis is a statistical claim about a population or data-generating process that serves as a reference assumption and is evaluated by a hypothesis test, often asserting no effect or difference.
- student's t-distributionuses · Student’s t-distribution is a family of continuous probability distributions with heavier tails than the normal distribution, used in inference when variability is estimated from data.
Questions about two-tailed test
What is two-tailed test?
A two-sided test is a hypothesis test in which sufficiently extreme results in either direction from the null value count as evidence against the null hypothesis.
Which Manning books explain two-tailed test?
Grokking Statistics and Timeless Algorithms, The Foundational Ideas.
What should I know before learning two-tailed test?
Manning books that teach two-tailed test usually introduce student's t-distribution first.
What is the difference between two-tailed test and one-sided test?
A two-sided test is a hypothesis test in which sufficiently extreme results in either direction from the null value count as evidence against the null hypothesis. A one-sided test is a hypothesis test whose alternative hypothesis and rejection region concern a departure from the null in one prespecified direction.
What is two-tailed test a kind of?
Two-tailed test is a kind of hypothesis testing. Hypothesis testing is a formal statistical procedure for evaluating evidence from observed data about a specified hypothesis, often a null hypothesis.
These guides are generated from the text of Manning books by Manning's knowledge graph and link to the sections they draw on. The full books are available on liveBook and at manning.com.

