This project was one of the individual assignments in RevoU as my practice of doing A/B Hypothesis Testing Analysis.

​

Background information

An e-commerce company is revamping a landing page after various analyses and research. The company wants to know whether the new landing page will give a better conversion rate before rolling out to a bigger audience.

​

Objective
Help the company decide which landing page is better than the other.

​

Analysis Method

​

​

​

​

Stated the null and alternative hypotheses below.

Null Hypothesis (H0)  :  The conversion rate on the new page is less than or equal to the conversion rate on the old page.

Alternative Hypothesis (H1)  :  The conversion rate on the new page is better than the conversion rate on the old page.

Then, I calculated the conversion rates for each group (control and treatment) and identified the significant difference between the calculated conversion rates using a one-tailed Z-test.

​

Result

Z-score = 0.5787432513872296

p-value = 0.2813812136899914

We don't have enough evidence to reject the null hypothesis because the p-value is more than 0.05. Thus, we accept the null hypothesis. The new landing page doesn't give a better conversion rate than the old one.

​

Recommendation

The company can keep using the old landing page because the hypothesis testing result shows that the conversion rate in the new landing page doesn't significantly differ from the one on the old landing page.