# What is media mix modeling (MMM)?

> Media mix modeling estimates each channel effect from years of weekly spend and results. Most indie games lack the data, so lift tests come first.

By Yos Riady. Updated 2026-11-18. Published 2026-11-18. Canonical URL: https://manalens.dev/glossary/media-mix-modeling

Media mix modeling, or marketing mix modelling (MMM), is a statistical model that estimates how much each marketing channel added to a result, from weekly spend and results over time. Google's Meridian guide asks for at least 2 years of weekly data for geo models, so most indie studios lack the history.

## Key points

- Google's Meridian guide asks for two years of weekly data for geo models and three years for national ones.
- Robyn recommends 1 variable for each 10 observations, so one year of weekly data supports about 5 variables.
- Manalens does not run MMM, so indie studios should start with attribution and lift tests.

## How much data does media mix modeling need?

Years of it. Google's Meridian guide asks for at least two years of weekly data for geo models and three years for national models. Meta's Robyn guide asks for at least two years of weekly data, and recommends 1 independent variable for each 10 observations.

Sources: Google Meridian documentation, Collect and organize your data; Robyn documentation, Analyst's guide to MMM.

## What does a worked example look like?

Example, our arithmetic: one year of weekly data gives 52 data points. At the Robyn ratio of 1 variable to 10 observations, that supports about 5 variables in total. A game needs a control for each festival, sale and big video, so no room is left for ad channels.

Meridian gives its own example: 12 media channels, 6 controls and 8 knots make 26 parameters, and two years of weekly data give 104 data points, which is 4 per parameter.

Sources: Robyn documentation, Analyst's guide to MMM; Google Meridian documentation, Amount of data needed.

## Why does media mix modeling matter for indie PC and web games?

Mostly as a warning. A small studio has short paid tests and big one-off beats, such as Next Fest or a creator video. Attribution to compare options, and lift tests to size the effect, work from the first week a Steam page is live.

MMM starts to make sense when several paid channels run all the time with steady spend, as for a publisher with a portfolio. Even then, Robyn recommends calibrating the model with incrementality studies on a regular basis.

- [Marketing mix modelling vs attribution for indie studios](https://manalens.dev/blog/marketing-mix-modelling-vs-attribution-games)
- [Cost per wishlist calculator](https://manalens.dev/tools/cost-per-wishlist-calculator)
- [A/B test significance calculator](https://manalens.dev/tools/ab-test-significance-calculator)

Sources: Robyn documentation, Analyst's guide to MMM; Google Meridian documentation, Collect and organize your data.

## Frequently asked questions

### Is media mix modeling worth it for an indie game?

Usually not before launch. Google's Meridian guide asks for two to three years of weekly data, and Meta's Robyn guide asks for 10 observations per variable. A studio with one or two channels gets more from tagged links and simple lift tests.

### Does Manalens run media mix modeling?

No. It does not run MMM, import ad spend or compute lift. It records visits, clicks, codes and installs per channel, runs six rule-based attribution models, imports the Steam UTM report and syncs daily wishlist adds per country (the automatic Steam sync is in early access), which you can use in your own lift tests.

### When does media mix modeling start to make sense?

When several paid channels run all the time with steady spend, and you have two or more years of weekly data. That is more typical of a publisher with a portfolio than of an indie game before launch. Even then, Robyn recommends calibrating the model with incrementality studies on a regular basis.

## Sources

- [Google Meridian documentation: Collect and organize your data (Google, read 18 November 2026)](https://developers.google.com/meridian/docs/pre-modeling/collect-data)
- [Google Meridian documentation: Amount of data needed (Google, read 18 November 2026)](https://developers.google.com/meridian/docs/pre-modeling/amount-data-needed)
- [Robyn documentation: Analyst's guide to MMM (Meta Open Source, read 18 November 2026)](https://facebookexperimental.github.io/Robyn/docs/analysts-guide-to-MMM/)

## Related guides

- [Incrementality](https://manalens.dev/glossary/incrementality)
- [Multi-touch attribution](https://manalens.dev/glossary/multi-touch-attribution)
- [Indie game marketing budget](https://manalens.dev/blog/indie-game-marketing-budget)
