What are your null and alternative hypotheses for this A/B test?

WHAT THIS TESTS: The interviewer wants to know if you can move beyond vague intuition and lock a business question into a formal statistical framework. Specifically, they are checking three things: whether you understand that the null hypothesis must contain equality and represent the status quo, whether you recognize that the prompt asks for a directional or one-sided alternative because it specifically asks if green increases registrations, and whether you precisely define the metric and population rather than speaking in generalities about button colors.

A GOOD ANSWER COVERS: First, state the null hypothesis as there being no difference in the registration conversion rate between the blue variant and the green variant for the targeted user population, which mathematically is often written as the difference in rates equals zero or the rates are equal. Second, state the alternative hypothesis as the registration conversion rate for the green variant being strictly greater than that of the blue variant, reflecting the directional nature of the business question. Third, explicitly name the exact metric such as registration conversion rate rather than just saying signups, name the two variants being compared, and name the population such as all users landing on the page during the experiment period. Fourth, optionally note that this setup implies a one-tailed test because the company only cares about an increase, not simply any difference.

COMMON WRONG ANSWERS: A major red flag is stating the null hypothesis as the blue button is better or that the green button does not work; the null must always represent no effect or no difference. Another red flag is proposing a two-tailed alternative such as the rates are not equal when the business question explicitly asks whether green increases registrations; this wastes statistical power and ignores the directional nature of the problem. A third red flag is forgetting to define the metric or population, for example saying the null is that the buttons are the same without clarifying what same means in terms of measurable user behavior.

LIKELY FOLLOW-UPS: The interviewer may ask how you would choose between a one-tailed and two-tailed test in practice, or what happens to your error rates if you switch to a two-tailed test after seeing the data. They might ask you to define the practical significance threshold, such as the minimum increase in registration rate that would justify a full rollout, or they might pivot to asking how you would randomize users and what sample size you need to achieve adequate power.

ONE CONCRETE EXAMPLE: Suppose the current blue button has a registration conversion rate of 12 percent. A precise null hypothesis would be that the conversion rate for the green button is equal to 12 percent for the population of users visiting the signup page during the two-week experiment. The alternative would be that the green button conversion rate is greater than 12 percent. This framing makes the subsequent steps clear: you will calculate a p-value for the observed difference under the assumption of no effect, and you will only reject the null if the green variant shows a statistically significant increase.

Source: Wikipedia: A/B testing