So, you’ve just run a test to try to improve average order size or average gift. Now you need to see if you results are statistically significant.

Here’s how you run a t-test in excel that will allow you to see if your difference in average gift is statistically significant.

First, you’ll need to install Excel’s data Analysis package.

  1. Click the Microsoft Office Button , and then click Excel Options.
  2. Click Add-Ins, and then in the Manage box, select Excel Add-ins.
  3. Click Go.
  4. In the Add-Ins available box, select the Analysis ToolPak check box, and then click OK.

Create an Excel spreadsheet with two columns. The first column should have the gift amounts from the control. The second column should have the gift amounts from the variant as shown below.

testing-2columns

Under the Data tab click on Data Analysis.

testing-datanalysis

Select the t-Test: Two-sample Assuming Unequal Variances.

testing-ttest

Select your data ranges for your two variables. Leave the Alpha unchanged at 0.05.

testing-ranges

After a few seconds, Excel will display your results in a new tab.

testing-testresults

To interpret the results you will want to look at the two-tail test because we want to understand if there is a difference in the means.

Because the p value of the test is .37627 is greater than .05 (our stated p value) we accept the null hypothesis which is that there was no difference in the means.