How we validated the impact a new offer would have on email acquisition
Alliance Defending Freedom
Alliance Defending Freedom is an alliance-building legal organization that advocates for the right of people to freely live out their faith.
Experiment Summary
Timeframe: 12/19/2018 - 01/11/2019
Alliance Defending Freedom had been running the current statement of belief on their blog pages as a method for email acquisition for well over three months. The statement related to one of their more recent cases, Jack Phillips, and focused on the need to fight back against government suppression of first amendment rights. Since it had been running for so long, we started to notice a decline in results as many of the visitors likely to convert had already done so.
With this finding, we decided to launch a new statement of belief. This time, we opted for a statement that would be more evergreen, one that didn’t rely on a specific case. We also wanted to try a more positive approach in the messaging to attract a different style of subscriber.
Research Question
Will a new offer yield better results than the long-standing Jack Phillips Statement of Belief?
Design
Results
Treatment Name | Conv. Rate | Relative Difference | Confidence | Average Gift | |
---|---|---|---|---|---|
C: | Fighting Back | 1.0% | $0.00 | ||
T1: | What We Are For | 1.3% | 25.3% | 98.2% | $0.00 |
This experiment has a required sample size of 12,874 in order to be valid. Since the experiment had a total sample size of 38,298, and the level of confidence is above 95% the experiment results are valid.
Flux Metrics Affected
The Flux Metrics analyze the three primary metrics that affect revenue (traffic, conversion rate, and average gift). This experiment produced the following results:
0% increase in traffic
× 25.3% increase in conversion rate
× 0% increase in average gift
Key Learnings
After running for nearly 3 weeks, we saw that the new statement of belief that focused on “What we are for” instead of “Fighting back” increased email acquisition by 25%. We also examined downstream donor conversion and noticed no significant difference between the two offers.
This finding will allow us to move forward with the new offer and continue to iterate our testing on the new control.
Question about experiment #9958
If you have any questions about this experiment or would like additional details not discussed above, please feel free to contact them directly.