UA Ledger · Measurement Lab · draft for review

Probabilistic plus deterministic rows: do not add them as one truth

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.

Enter deterministic attributed conversions, probabilistic or modelled conversions, and the count already present in both methods after an authorised join. Report each method and the overlap; do not present the sum as incremental conversions.

Calculated outputs

Assumption sensitivity

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

Equations

• Naive sum: det+prob
• Distinct rows: det+prob-both
• Overlap share of naive %: 100*both/(det+prob)

Constraints: (both<=det) && (both<=prob).

Limits

Vendor modelling methods differ and are often undocumented in public help pages. This does not validate any vendor’s probabilistic matcher.

AppsFlyer attribution model · documentation cited 19 September 2026.