UA Ledger · Measurement Lab · draft for review

Hold segment weights fixed when a blended retention rate moves

Synthetic teaching inputs. No real campaign results or industry defaults. Change the values to inspect the model. Calculations run locally; this page sends no data and does not retain inputs after closing.

Enter two segment retention rates and the share of the first segment in each reporting period. Calculate each blended rate as the weighted sum of the two segment rates. Keep the segment definitions stable and use complete, mutually exclusive populations. The exercise is deliberately simple so the contribution of the weights remains inspectable.

Calculated outputs

Assumption sensitivity

Only mixAfter varies; all other inputs are held constant. This is not a probability range.

Equations

• Before blended retention %: 100*(rateA*mixBefore+rateB*(1-mixBefore))
• After blended retention %: 100*(rateA*mixAfter+rateB*(1-mixAfter))
• Composition-only difference points: 100*(rateA-rateB)*(mixAfter-mixBefore)

Additional constraints: (rateA<=1) && (rateB<=1) && (mixBefore<=1) && (mixAfter<=1). The field minimums also apply.

Limits

Two segments rarely capture every confounder. This is a standardisation illustration, not a causal adjustment or a claim that real segments would retain fixed performance after a large budget change.

Google Analytics BigQuery Export schema · primary documentation checked 19 September 2026.