XLSTAT: Cochran's C test to detect outlying variances in Excel

This tutorial will help you run a Cochran C test to detect outlying variances and interpret the results in Excel using XLSTAT.

Background

The Cochran's C test is a statistical technique used to detect whether the largest variance in a dataset is significantly different from the other variances.

Dataset for Example

Four samples have been obtained from two different distribution: 3 with a normal distribution with mean 0 and variance 2 and one with a normal distribution with mean 0 and variance 5. wish to test if there is a variance larger than the others

Goal of this tutorial

We would like to detect if a variance is larger than the others using the Cochran's C test.

Setting Up

• Open XLSTAT.
• Click on the Testing outliers menu and select the Cochran's C test feature:

In the General tab:

• Select the four columns, each representing a different group or sample.
• Set the Data format to One column per group.

In the Options tab:

• Select the Inlying option as the alternative hypothesis.
• Leave the significance level at the default value of 5% (0.05).

• Click on the OK button to launch the computations.
• The results are displayed on a new Excel sheet.

Interpreting the Results

The result is that the p-value for this test is smaller than 0.0001. That means that the null hypothesis should be rejected.

In the following table, the detected variances and outliers are given.

Then, a graphic with all variances represented is displayed.

We have shown that there is an outlying variance in our dataset.