# Acquisition Cohort Comparison Brief

Canonical page: https://waitlist.crany.ai/marketing-templates/acquisition-cohort-comparison-brief

By Tangenix. Published 2026-10-24. Category: Acquisition measurement.

Compare acquisition groups with aligned entry rules, return outcomes and observation windows while preserving audience-mix and incomplete-follow-up limits.

## Task

Design a fair descriptive comparison between acquisition cohorts before interpreting their outcomes.

## When to use

Use this when a founder wants to compare people arriving through different periods or channels. Specify who enters each group, how long they can be observed and what later behavior means.

## Choose another approach when

You plan to compare a mature group with yesterday’s signups as if both had equal opportunity, or intend to claim channel causality from self-selected audiences.

## Inputs

- A clear acquisition grouping rule and stable unit.
- A relevant later-use or task outcome with validated measurement.
- Entry dates, follow-up availability and known differences in audience or access.

## Template

    Comparison question / definition version: [descriptive purpose]
    Cohort A / B entry conditions: [dates, channel or other actual criterion]
    Unit and overlapping membership: [deduplication or explicit overlap]
    Outcome / return criterion: [specific observed behavior]
    Follow-up interval and timezone: [same opportunity for both groups]
    Maturity cutoff: [which entries have a complete window]
    Include / exclude / not yet observable: [predeclared rules]
    Access and product-version differences: [material exposure]
    Audience-mix and selection differences: [known or unknown]
    Measurement limits: [device scope, consent and missing events]
    Observed outcome with denominator: [actual report or pending]
    Uncertainty and alternative explanation: [include sparse samples]
    Interpretation permitted: [bounded descriptive statement]
    Next investigation: [what evidence could distinguish explanations]
    An observed difference is not a randomized estimate of a channel’s causal effect.

## Illustrative example

This is not a Crany customer result. Replace example details with verified facts.

    Fictional example: a founder wants to compare pilot applicants from a tutorial with people who joined after a community discussion. The tutorial group has had time to receive access, while recent discussion signups are still waiting.
    The brief aligns the entry and follow-up rules before examining later checklist use. People without access are not counted as failed product users. The founder also records that the tutorial explained the task in detail, so the groups may differ before signup.
    If the mature groups remain small, the conclusion stays descriptive. No retention percentage is fabricated, and the comparison is not called a controlled test just because both groups appear in the same table.

## How to use

1. Define group membership, outcomes and overlap before selecting favorable dates.
2. Align follow-up maturity and document product-access and audience differences.
3. Report bounded comparisons with uncertainty and the next evidence needed.

## Checks

- Incomplete follow-up is not recorded as a failed outcome.
- The counting unit and outcome definition match across groups.
- Self-selection and different product exposure remain interpretation limits.

## What to measure

Track how much of each cohort has a complete eligible observation window, then compare the stated outcome under a stable definition. Preserve uncertainty from sparse samples and missing data. A descriptive cohort contrast does not by itself justify a causal channel-return claim.

## Research and sources

Google explains cohort entry and return criteria and provider-specific device-based limitations. Microsoft discusses trustworthy experiment measurement. This original comparison brief remains descriptive and does not import GA4 behavior into every provider or imply random assignment.

- [Google Analytics: Cohort exploration](https://support.google.com/analytics/answer/9670133?hl=en) — checked 2026-10-24. Cohort inclusion and return criteria, time granularity and GA4 device-based limits. Provider-specific behavior does not imply cross-device identity completeness.
- [Microsoft Research: Patterns of Trustworthy Experimentation, Pre-Experiment Stage](https://www.microsoft.com/en-us/research/articles/patterns-of-trustworthy-experimentation-pre-experiment-stage/) — checked 2026-10-24. Clear hypotheses, appropriate measurement, assignment units and data-quality checks before a controlled experiment.

Prepared with AI assistance. Sources support the stated principles; they do not endorse Crany or guarantee performance.

## About Crany

Crany is an AI marketing co-founder in development for software founders and vibe coders. It is designed to strategize, execute approved marketing and improve based on results. These free resources are usable independently of app access. The public waitlist is at https://waitlist.crany.ai/.