# SRM Checks

> For AI agents: a documentation index is available at [/llms.txt](/llms.txt). Append `.md` to any page URL for markdown, or send `Accept: text/markdown`.

## SRM - sample ratio mismatch

Sample ratio mismatch (SRM) occurs when the observed allocation of **unique** users between test groups differs from the expected allocation or split of the test. Refer to the [Statsig blog post on sample ratio mismatch](https://www.statsig.com/blog/sample-ratio-mismatch) for background.

SRM is a signal that there may be unknown bias in the test. Unknown bias is a significant problem because, without a clear diagnosis of the imbalance, it's difficult to know how much the bias affects your results.

## SRM checks

Statsig runs SRM checks on all experiments and feature gates as part of Health Checks (refer to [Health Checks](https://docs.statsig.com/experiments/monitor)). Statsig uses a Chi-squared test to identify whether the split of users between groups indicates a sample ratio mismatch.

![SRM health check results interface](https://docs.statsig.com/images/experiments/srm-checks-health.png)

Statsig automatically analyzes data by common dimensions that the Statsig SDK logs to identify potential drivers of SRM. These include sdk\_type, sdk\_version, reason, is\_bot, browser\_name, browser\_version, os, os\_version, and region.

![SRM dimension analysis breakdown](https://docs.statsig.com/images/experiments/srm-checks-dimensions.png)