NannyML / The-Little-Book-of-ML-Metrics

The book every data scientist needs on their desk.
https://www.nannyml.com/metrics
757 stars 60 forks source link

A/B Testing and A/A Testing #92

Closed kasthuri7903 closed 1 month ago

kasthuri7903 commented 1 month ago

Metric's name A/B Testing and A/A Testing

Metric's category Business Metrics

Metrics formula image

Describe the metrics use cases and any relevant references. A/B Testing: Used to compare two versions of something (like a webpage or app feature) to see which one performs better. It helps make decisions based on data to improve user engagement or sales.

A/A Testing: Used to check if the testing process itself is reliable before running an A/B test. It ensures that there are no errors or biases in the way data is collected.

Additional context These metrics are useful for making data-driven decisions and improving performance in areas like marketing and product development.

santiviquez commented 1 month ago

Interesting. Would you include them as A/B and A/A testing metrics per se, or list Conversion Rate independently and then explain that it is often used in A/B testing experiments? Because many metrics can be evaluated through A/B experiments.

kasthuri7903 commented 1 month ago

Thank you for your input! I agree that listing Conversion Rate as a standalone metric makes more sense. I would like to describe A/B and A/A testing as experimental frameworks that help measure and compare metrics like Conversion Rate, Bounce Rate, and others.

santiviquez commented 1 month ago

Great. To keep track of the Conversion Rate and Bounce Rate, I'll create two separate issues and close this one.

santiviquez commented 1 month ago

95 Conversion Rate

96 Bounce Rate

kasthuri7903 commented 1 month ago

Great! I’d like to take the lead on creating the content for both Conversion Rate and Bounce Rate metrics. I appreciate your guidance throughout this process, so please let me know if there are any specific points or resources I should consider while working on this.

santiviquez commented 1 month ago

Hi @kasthuri7903, the usual workflow looks like this:

  1. Fork this repository
  2. Clone the forked repo to your local env
  3. Create a new branch before you make any
  4. Make the desired changes
  5. Commit and push your changes to your forked repo
  6. Open a Pull Request from github.com

That is pretty much it. This video summarizes it nicely: https://www.youtube.com/watch?v=8lGpZkjnkt4

You might need to install latex on your own machine. In case you don't have it, check out this instructions.

For the specific content of the metrics, feel free to run your own research. Then, while reviewing the PR, we can iterate in case you have any issues with the visuals or latex formatting for the formulas.

Let me know if you need any help.

kasthuri7903 commented 1 month ago

Thanks for the instructions! I’ll follow the steps and start working on the Conversion Rate and Bounce Rate content.