Daily active users, revenue, clicks on “add to shopping cart,” etc. Within Statsig, we celebrate these increases when they are statistically significant with a deep, satisfying, green color:
But what about when this isn’t the case?
You might want to measure things that are not always better when they go up, like
the count of crashes in your app
removals of items from a shopping cart
page loading time
For all of these, if we see significant increases, we want everyone using the platform to recognize that this is not desired.
In Statsig, we make this easy now from the detail page for any metric. Just click into the overflow menu and look for “Set Metric Directionality.”
From there, simply choose whether an increase or a decrease is desired for this metric, and confirm!
We ran into a case like this at Statsig when we ran an experiment to load content from the next page when your cursor hovers on the link, since you might visit there imminently. After collecting data for several weeks, we saw that we significantly reduced the time it takes to load a page (avg_time_to_first_paint)!
Yet, this was displayed in a harsh red color, giving the impression that this effect isn’t what we want. At a glance, people might overlook the meaning of the metric here and draw the wrong conclusion.
After setting the directionality of avg_time_to_first_paint to “Decrease,” that effect is now illustrated in the satisfying green color it deserves!
You can use Statsig to measure all kinds of things you care about, through all of the ups and downs of product development!
What will your team measure?
Take our “sandbox” project for a spin! In this project, we have generated real-time sample data for you to explore and experiment with.
Thanks to our support team, our customers can feel like Statsig is a part of their org and not just a software vendor. We want our customers to know that we're here for them.
Migrating experimentation platforms is a chance to cleanse tech debt, streamline workflows, define ownership, promote democratization of testing, educate teams, and more.
Calculating the right sample size means balancing the level of precision desired, the anticipated effect size, the statistical power of the experiment, and more.
The term 'recency bias' has been all over the statistics and data analysis world, stealthily skewing our interpretation of patterns and trends.
A lot has changed in the past year. New hires, new products, and a new office (or two!) GB Lee tells the tale alongside pictures and illustrations:
A deep dive into CUPED: Why it was invented, how it works, and how to use CUPED to run experiments faster and with less bias.
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.