Business Context

StreamCart launched a new in-app onboarding tooltip meant to increase adoption of its saved-payment feature. The analytics team wants a quick statistical analysis and a simple visualization plan in Python or R to determine whether the tooltip changed adoption meaningfully.

Problem Statement

You are given results from a randomized experiment comparing the old experience (control) with the new tooltip (treatment). Determine whether the treatment increased the saved-payment adoption rate, quantify the uncertainty, and describe what visualizations you would produce to communicate the result.

Given Data

Additional parameters:

Requirements

1. State the null and alternative hypotheses.
2. Compute the sample proportions and the absolute lift.
3. Calculate the pooled proportion and standard error for the hypothesis test.
4. Compute the z-statistic and two-sided p-value.
5. Construct a 95% confidence interval for the difference in adoption rates.
6. State whether the result is statistically significant at the 5% level.
7. Briefly describe two visualizations you would create in Python or R to present the result.

Assumptions

• Users were randomly assigned to control and treatment.
• Each user appears once in the analysis.
• The normal approximation is appropriate because both groups have sufficiently large sample sizes and success/failure counts.