Case Study on How Not to Design a Data-Driven Experiment

In an attempt to increase its renewal rate, NTEN learned several valuable lessons in how not to design a data-driven experiment. The top five takeaways: 1. Don't change too many variables. 2. Set up a control case. 3. Plan out the full experiment ahead of time, including the analysis. 4. Start with small, easy-to-design experiments. 5. Double check your plan against the scientific method.