Question

Imagine that you want to run an A/B test, and you think the treatment will improve your corversion rate, which is 10%. In that scenario, what is your null hypothesis?

a. The treatment will have a conversion rate of less than 104 ;
b. The corversion rate in the control group is equal to the conversion rate in the treatnent group
c. The treatment will have a significant improvement in conversion rate
d. The treatrient will have no conversions

Answer 1

The null hypothesis in an A/B test, where a treatment is believed to improve a conversion rate of 10%, is that there is no difference between the conversion rate in the control group and the treatment group (option b).

Step-by-step explanation:

The null hypothesis in an A/B test usually states that there is no effect or no difference between the treatment and the control group. When you think the treatment will improve your conversion rate, which is currently 10%, the null hypothesis would be: "The conversion rate in the control group is equal to the conversion rate in the treatment group." Therefore, the correct answer is (b) The conversion rate in the control group is equal to the conversion rate in the treatment group.

In hypothesis testing, the alternative hypothesis is what you want to try to prove, and it is based on the notion that the treatment will have a positive effect. For instance, the alternative hypothesis in this case might state that the conversion rate in the treatment group is higher than in the control group. The null hypothesis must contradict the alternative hypothesis and is the default assumption that there is no difference between groups until proven otherwise.