Introducing Holdouts

Alex Coleman
Sat May 22 2021

Measuring the combined impact of multiple features

Your team is busy shipping features, and they are keeping a close eye on product metrics. While it’s easy (with Statsig) to understand the impact of individual feature launches, one question that often comes up is: What’s the collective impact of multiple features?

At Facebook, every team calculated the cumulative impact of all features shipped over the last 6 months. And to do that accurately, we use “Holdouts” that we create at the beginning of each half. A holdout is usually small (1–5%) in size, and as the name implies, holds that set of people out of any new features launched during that half. This provides us with a baseline to measure the cumulative impact of multiple launches over 6 months. At the end of the half, we release that holdout and create a new one for the next half. Holdouts are powerful and have many other uses including measuring long-term effects, quantifying subtle ecosystem changes, and debugging metric movements.

Today, we’re making all this available via Holdouts on Statsig. Setting up a holdout is a cinch — you pick the size and the features you want held from users. You can also make holdouts be ‘global’ which means all new features will automatically respect the holdout. And occasionally (hopefully, sparingly) you might want to run a “back-test” and you can do that by turning on holdouts to an existing set of features.

Once set up, our Pulse engine will automatically compute the impact of all those features compared against the baseline. No additional configuration or code necessary.

Go ahead, try it out today! We have a free plan that allows you to get going right away without needing to talk to any sales teams.

Try Statsig Today

Explore Statsig’s smart feature gates with built-in A/B tests, or create an account instantly and start optimizing your web and mobile applications. You can also schedule a live demo or chat with us to design a custom package for your business.


Recently published

My Summer as a Statsig Intern


This summer I had the pleasure of joining Statsig as their first ever product design intern. This was my first college internship, and I was so excited to get some design experience. I had just finished my freshman year in college and was still working on...

Read more

Long-live the 95% Confidence Interval


The 95% confidence interval currently dominates online and scientific experimentation; it always has. Yet it’s validity and usefulness is often questioned. It’s called too conservative by some [1], and too permissive by others. It’s deemed arbitrary...

Read more

Realtime Product Observability with Apache Druid


Statsig’s Journey with Druid This is the text version of the story that we shared at Druid Summit Seattle 2022. Every feature we build at Statsig serves a common goal — to help you better know about your product, and empower you to make good decisions for...

Read more

Quant vs. Qual


💡 How to decide between leaning on data vs. research when diagnosing and solving product problems Four heuristics I’ve found helpful when deciding between data vs. research to diagnose + solve a problem. Earth image credit of Moncast Drawing. As a PM, data...

Read more

The Importance of Default Values


Have you ever sent an email to the wrong person? Well I have. At work. From a generic support email address. To a group of our top customers. Facepalm. In March of 2018, I was working on the games team at Facebook. You may remember that month as a tumultuous...

Read more

CUPED on Statsig


Run experiments with more speed and accuracy We’re pleased to announce the rollout of CUPED for all our customers. Statsig will now automatically use CUPED to reduce variance and bias on experiments’ key metrics. This gives you access to a powerful experiment...

Read more

We use cookies to ensure you get the best experience on our website.

Privacy Policy