# Null Hypothesis Testing Overview

Lesson 2: T-Test Comparing Two Groups

In this lesson, we’ll dig into one of the most common methods for null hypothesis testing: the t-test. If we can show that the trends in the current data are not explainable as just random chance, then we can infer they are likely to continue. For example, if Team A is outperforming Team B, and the difference is “statistically significant,” we can infer this is a real difference (as opposed to a temporary coincidence) and conclude that Team A truly is better.

Lab: T-Test

Imagine your company has hired two different freelance teams, Team X and Team Y, for a number of projects. For each project, the profit for your company is reported. In this lab, you’ll calculate each team’s mean profit and standard deviation. Then you’ll use a t-test to determine whether the difference in each team’s performance is statistically significant (and likely to continue in the future) or just due to random chance.

The data set for this lab can be viewed here. From the link, copy and paste all the data into a new worksheet in Excel Online.