A hypothesis test is exactly what it sounds like: You make a hypothesis about the parameters of a population, and the test determines whether your hypothesis is consistent with your sample data.

- Hypothesis TestingPenn State University tutorial
- Hypothesis TestingWolfram MathWorld overview
- Hypothesis TestingMinitab Blog entry
- List of Statistical TestsA list of commonly used hypothesis tests and the circumstances under which they're used.

The p-value of a hypothesis test is the probability that your sample data would have occurred if you hypothesis were *not* correct. Traditionally, researchers have used a p-value of 0.05 (a 5% probability that your sample data would have occurred if your hypothesis was wrong) as the threshold for declaring that a hypothesis is true. But there is a long history of debate and controversy over p-values and significance levels.

Many of the most commonly used hypothesis tests rely on assumptions about your sample data—for instance, that it is continuous, and that its parameters follow a Normal distribution. Nonparametric hypothesis tests don't make any assumptions about the distribution of the data, and many can be used on categorical data.

- Nonparametric Tests at Boston UniversityA lesson covering four common nonparametric tests.
- Nonparametric Tests at Penn StateTutorial covering the theory behind nonparametric tests as well as several commonly used tests.

- Last Updated: Aug 16, 2024 1:12 PM
- URL: https://guides.library.duq.edu/quant-methods
- Print Page

Subjects: Data, Education, Mathematics, Political Science, Social Sciences