A Sample Ratio Mismatch (SRM) error occurs when the actual allocation of participants to different groups in an experiment deviates from the intended or planned allocation ratio. For example, if you plan for a 50-50 split (50% of participants in Group A and 50% in Group B) but due to a technical issue or implementation mistake, the allocation becomes 60-40, that would be a Sample Ratio Mismatch error. GrowthBook sets the default P-value to 0.001, which means there is a very, very low probability that the SRM was caused by random chance. This error is observed almost exclusively when there’s been a mistake in the implementation [[source](https://linen.growthbook.io/t/16321824/is-sample-ratio-mismatch-srm-detected-p-value-below-0-001-si)]. To troubleshoot this issue, you can start by checking the following areas: 1. The trackingCallback configuration: The trackingCallback you configure is used by the SDK to send tracking events to your data warehouse whenever a user is exposed to an experiment. Make sure that whether the trackingCallback method sends event data is not conditional on the experiment variation [[source](https://docs.growthbook.io/kb/experiments/troubleshooting-experiments#problem-2-srm-errors-traffic-imbalance-in-the-experiment)]. 2. Activation Metric: If you are using an Activation Metric that is triggered differently by users across variations, it could cause a traffic imbalance. 3. Hash Attribute and Identifier Type: Ensure that the Hash Attribute matches the "Identifier Type" in your data source. 4. Changes to the experiment targeting: If you made a change to the experiment targeting after it started, or created a new phase without re-randomizing, it could lead to a Sample Ratio Mismatch. If you are running a URL Redirect test, there might be additional considerations. Unfortunately, the provided sources do not contain specific information about SRM errors in URL Redirect tests. For more detailed troubleshooting, you may want to refer to the [GrowthBook documentation](https://docs.growthbook.io/kb/experiments/troubleshooting-experiments#problem-2-srm-errors-traffic-imbalance-in-the-experiment) or seek advice from the GrowthBook community.