Products
Solutions
Resources
Docs Pricing
Sign In Contact Us

Statsig Blog

The Statsig Blog covers the latest in feature management, experimentation, analytics, and more
Liz Obermaier
Data Scientist, Statsig

Liz Obermaier is a Data Scientist with a flair for explaining complicated concepts like sample ratio mismatch and p-value to people who have never considered them before (like biography writers) in a way that makes sense.

At Meta, Liz practiced data science on the VR/AR technologies team, with a focus on ensuring that new technology is helpful and beneficial to users.

In her free time, Liz can be found hanging out with her dog, Kiwi, who is very polite and never barks during meetings.
Calculate exact relative metric deltas with Fieller intervals
Liz Obermaier
Tue Jun 10 2025
Fieller intervals are an exact, analytic solution for calculating a ratio’s confidence interval. Available for relative metric deltas in Statsig now.
Introducing surrogate metrics
Liz Obermaier
Mon May 12 2025
Learn how Statsig supports surrogate metrics in experiments by accounting for model prediction error in p-values and confidence intervals.
Designing controlled experiments to test correlated metrics
Liz Obermaier
Fri Mar 28 2025
Learn how correlated metrics affect experiments, from surrogate and intrinsic metrics to pitfalls in multiple comparison corrections.
How Statsig uses query-level experiments to speed up Metrics Explorer
Nicole Smith, Liz Obermaier
Thu Feb 20 2025
Experimenting with query-level optimizations at Statsig: How we reduced latency by testing temp tables vs. CTEs in Metrics Explorer.
Controlling your type I errors: Bonferroni and Benjamini-Hochberg
Liz Obermaier
Wed Jul 31 2024
The Benjamini-Hochberg procedure on Statsig reduces false positives in experiments by adjusting significance levels for multiple comparisons, ensuring reliable results.
Introducing Differential Impact Detection
Liz Obermaier
Wed Jul 17 2024
Introducing Differential Impact Detection: Identify how different user groups respond to treatments and gain useful insights from varied experiment results.
How to track your features' retention
Liz Obermaier
Fri May 17 2024
Explore flexible retention metrics beyond simple return rates. Learn to define meaningful actions and timeframes, manage seasonality, and use Statsig for detailed insights.
A quick guide to sample ratio mismatch (SRM)
Liz Obermaier
Thu Aug 31 2023
A lack of “fairness” is called SRM or sample ratio mismatch. For instance, flipping a biased coin that doesn't land on heads and tails equally.
Older Posts Show All

Loved by customers at every stage of growth

See what our users have to say about building with Statsig
Testimonials
We use cookies to ensure you get the best experience on our website.
Privacy Policy