# Degrees of Freedom

*Math & Statistics — Finicade finance glossary*

Degrees of freedom is the number of values in a calculation that are free to vary once constraints are imposed. Estimating a mean uses one up, which is why sample variance divides by n−1 rather than n. In regression it's observations minus parameters, and it formalises a practical warning: fit enough parameters relative to your data and the model can explain everything while knowing nothing.

**Also known as:** df, degrees of freedom statistics

**Related terms:** [Student's t-Distribution](https://finicade.com/glossary/students-t-distribution), [Chi-Square Test](https://finicade.com/glossary/chi-square-test), [t-Test](https://finicade.com/glossary/t-test), [Regression](https://finicade.com/glossary/regression), [Overfitting](https://finicade.com/glossary/overfitting)

**Taught in:** Stat Dojo — The Chi-Square Test

Source: https://finicade.com/glossary/degrees-of-freedom