# Classify Statistical Outliers

**Classify Statistical Outlier** is another type of noise classifier. This routine first creates a surface from a neighborhood of points (**Neighbor Count**). Then, residuals in respect to this surface are computed for each point. Any points with residuals that fall outside of the sigma specified (**Sigma Multiplier**) are assigned to the **Output Class**.

In the example below, any points with a residual larger than sigma 1.0 are assigned to the Low Point (noise) class:

<figure><img src="/files/XFtDT3ATKARSEK3GiJZN" alt=""><figcaption></figcaption></figure>

This tool is ideal for cleaning high density data sets and for tightening up planar surfaces. In general, the **Sigma Multiplier** parameter controls how aggressively this tool classifies points as noise. Below are some example values:

| Sigma Multiplier Value | Use-case                                                                                                                         |
| ---------------------- | -------------------------------------------------------------------------------------------------------------------------------- |
| 3.00                   | Will classify very few points as noise. Ideal for high-precision point clouds.                                                   |
| 1.00                   | Will classify a moderate amount of points as noise, and generally a good starting point when experimenting with outlier removal. |
| 0.5                    | Will classify about half of the data set as noise, and useful when attempting to drastically improve low precision data sets.    |


---

# Agent Instructions: Querying This Documentation

If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter:

```
GET https://docs.phoenixlidar.com/spatialexplorer-8-and-9/user-interface/toolbars/analytics/classify/classify-statistical-outliers.md?ask=<question>
```

The question should be specific, self-contained, and written in natural language.
The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.