# Residual

*Math & Statistics — Finicade finance glossary*

A residual is the gap between an observed value and what the model predicted. Residuals are where the diagnostics live: if they fan out with the fitted value you have heteroskedasticity, if today's predicts tomorrow's you have autocorrelation, and if they curve you have the wrong functional form. Plotting them is the single most informative thing you can do after fitting a regression.

**Also known as:** residuals, error term, regression residual

**Related terms:** [Ordinary Least Squares](https://finicade.com/glossary/ordinary-least-squares), [Regression](https://finicade.com/glossary/regression), [Heteroskedasticity](https://finicade.com/glossary/heteroskedasticity), [Autocorrelation](https://finicade.com/glossary/autocorrelation), [R-Squared](https://finicade.com/glossary/r-squared)

**Taught in:** Stat Dojo — Prediction & RMS Error

Source: https://finicade.com/glossary/residual