Sample size and running time - Docs - PostHog
posthog.com · 1,034 words · saved by 1 readers
When creating an experiment, we provide recommended running times and sample sizes based on the parameters you choose. These values serve as…
Running time and sample size Contents Finding the calculator Calculation modes Automatic mode Manual mode Minimum detectable effect (MDE) Understanding the results Tips for accurate estimates Before running an experiment, you'll want to know how long it needs to run to get reliable results. The running time calculator helps you estimate this based on your traffic and the size of effect you want to detect. Finding the calculator The running time indicator appears on your experiment page, showing the estimated remaining time and a progress indicator: Click the gear icon next to the time estimate
related reading
- Bayesian statistics - Docs - PostHogposthog.com
- All About Rooflines | How To Scale Your Modeljax-ml.github.io
- Legacy statistics methodology - Docs - PostHogposthog.com
- PostHog – We make your product self-drivingposthog.com
- What is Effect Size and Why Does It Matter? (Examples)scribbr.com
- A/B testing mistakes I learned the hard way - PostHogposthog.com
- Estimating training compute of deep learning models | Epoch AIepochai.org
- Optimal experimental design - Wikipediaen.wikipedia.org
- GitHub - google-research/tuning_playbook: A playbook for systematically maximizing the performance of deep learning models.github.com
- German tank problem - Wikipediaen.wikipedia.org
- Sampling Variability - MathBitsNotebook(A2)mathbitsnotebook.com
- Big O Cheat Sheet – Time Complexity Chartfreecodecamp.org