How the landing page design can affect conversion
Texas State Historical Association
Experiment Summary
Timeframe: 06/24/2015 - 09/25/2015
A recent experiment was done to bring older landing pages up to the latest levels of optimization. However, what this experiment proved is that a design that works for one page may have the adverse reaction on another. Based upon these results, we decided to revalidate the main Heritage donation page to ensure that we were using a design that was achieving the best possible results for us.
Research Question
Which design will allow for the greatest number of gifts and revenue?
Design
Results
| Treatment Name | Conv. Rate | Relative Difference | Confidence | |
|---|---|---|---|---|
| C: | Secured Template | 38.3% | ||
| T1: | Join Heritage Template | 31.9% | -16.7% | 76.9% |
This experiment has a required sample size of 429 in order to be valid. Unfortunately, the required sample size was not met and a level of confidence above 95% was not met so the experiment results are not valid.
Key Learnings
After 90 days, this test had not yet reached statistical significance so we decided to turn it off in order to move to the next experiment. However, based upon a level of confidence above 85%, we can classify this as “approaching validity.” This result reinforces that the current simple design of the main donation page is effective with the current amount of copy.