Analyze AB test results

This project was completed as part of the course requirements of Udacity's Data Analyst Nanodegree certification.

Overview

The project conducted A/B testing of user conversions on an old and new wepage.

Steps to prepare data for testing:

included handling mismatched condition and page assignment
removing duplicate ids
removing null rows if present
datatype of all the columns

Statistical Analysis

Bootstrapping sampling distributions and p-value calculations
hypothesis testing via bootstrapping
Z-core tests
Logistic regression
Multiple linear regression modelling to assess for interactions of independent variables

Technologies Used

Python
Numpy
Pandas
Matplotlib
StatsModels
Scipy
LaTex
Jupyter Notebook

Key Findings

The conversion rate for the new page was not superior to that for the old page
The country of the user did not impact the rate of conversion between the new and the old page
The timestamp did not impact the rate of conversion between the new and the old page