Skip to content

Commit

Permalink
Update AB_Testing.md
Browse files Browse the repository at this point in the history
  • Loading branch information
leya-595 authored Nov 10, 2023
1 parent 22bc1a5 commit 9db138b
Showing 1 changed file with 7 additions and 7 deletions.
14 changes: 7 additions & 7 deletions Topics/User_Experience/AB_Testing.md
Original file line number Diff line number Diff line change
Expand Up @@ -6,23 +6,23 @@ A/B testing is a research method used to compare two versions of a web page or m
## **Steps/How To:**
**Identify Changes:** Identify any potential problem areas within the UI and create a hypothesis of how to fix it <br />

###**Create Variation:** Create two versions of the applications UI to run the experiment on, create the new design based on the hypothesis, whether it be changing the font, colors, or re-designing the whole page. <br />
**Create Variation:** Create two versions of the applications UI to run the experiment on, create the new design based on the hypothesis, whether it be changing the font, colors, or re-designing the whole page. <br />
- The original page is known as the control.
- The altered page is known as the variation.

###**Running The Experiment:** Randomly filter the traffic of the application where one group (Group A) sees the original, or controlled version, and the other group (Group B) sees the modified version. <br />
**Running The Experiment:** Randomly filter the traffic of the application where one group (Group A) sees the original, or controlled version, and the other group (Group B) sees the modified version. <br />

###**Collect Data:** Record and measure different metrics such as user session duration or other performance metrics related to the application. <br />
**Collect Data:** Record and measure different metrics such as user session duration or other performance metrics related to the application. <br />

###**Analyze Results:** Based on the results, determine which version improves performance and deploy the winning variation. The experiment can be repeated to make further improvements. <br />
**Analyze Results:** Based on the results, determine which version improves performance and deploy the winning variation. The experiment can be repeated to make further improvements. <br />

## **Types of A/B Testing:**
**Split URL Testing:**
- Split URL testing is a variation of A/B testing where two different web page urls are used, rather than running the experiment on the same url. Used for testing completely new page designs.
- Split URL testing is a variation of A/B testing where two different web page urls are used, rather than running the experiment on the same url. Used for testing completely new page designs. <br />
**Multivariate Testing:**
- Multivariate testing tests various changes to different page elements simultaneously to analyze which combinations perform the best. Can be used to save time rather than performing multiple A/B experiments.
- Multivariate testing tests various changes to different page elements simultaneously to analyze which combinations perform the best. Can be used to save time rather than performing multiple A/B experiments. <br />
**Multi-Page Testing:**
- Multi-Page testing tests changes to an element on the web page over multiple pages within the website. Allows for a consistent set of pages when testing variation with control.
- Multi-Page testing tests changes to an element on the web page over multiple pages within the website. Allows for a consistent set of pages when testing variation with control. <br />

## **Benefits of A/B Testing:**
- Optimizes user experience which allows you to create a more effective application.
Expand Down

0 comments on commit 9db138b

Please sign in to comment.