Winsorization in Warehouse Native
Apply winsorization in Statsig Warehouse Native to cap extreme metric values at chosen percentiles, stabilizing experiment scorecards against outliers.
Statsig Warehouse Native lets you configure winsorization per metric to cap extreme values and reduce outlier noise in experiment results. Winsorization measures the percentile Px of a metric and sets all values over Px to Px.
Statsig computes the Px value using all non-zero and non-null unit-level values of the metric. Statsig aggregates metrics from rows or events, then uses the Px'th unit's value as the threshold to adjust other units' values.
At Statsig, the default percentile for winsorization is 99.9%. Winsorization at this percentile reduces the influence of extreme outliers caused by factors such as logging errors or bad actors.
Statsig applies winsorization to sum, event count, mean, ratio, and funnel metrics, including imported metrics. Statsig doesn't apply winsorization to Participation or User Accounting metrics.
Metric capping
Metric capping is an effective technique for handling outliers. You can define maximum values for a metric for any unit type configured for that metric. Statsig automatically adjusts any value exceeding the cap downward to the cap value.
For example, if purchases greater than $10,000 per day shouldn't skew analysis, Statsig adjusts any transaction exceeding that threshold downward to the limit. Metric capping supports Event Count and Aggregation (sum) metric types.
Was this helpful?